[ { "key": "AGKNTCNP", "version": 786, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/AGKNTCNP", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/AGKNTCNP", "type": "text/html" } }, "meta": { "creatorSummary": "Bullock et al.", "parsedDate": "2020-05", "numChildren": 2 }, "data": { "key": "AGKNTCNP", "version": 786, "itemType": "conferencePaper", "title": "Overlap-Aware Diarization: Resegmentation Using Neural End-to-End Overlapped Speech Detection", "creators": [ { "creatorType": "author", "firstName": "Latané", "lastName": "Bullock" }, { "creatorType": "author", "firstName": "Hervé", "lastName": "Bredin" }, { "creatorType": "author", "firstName": "Leibny Paola", "lastName": "Garcia-Perera" } ], "abstractNote": "We address the problem of effectively handling overlapping speech in a diarization system. First, we detail a neural Long Short-Term Memory- based architecture for overlap detection. Secondly, detected overlap regions are exploited in conjunction with a frame-level speaker posterior matrix to make two-speaker assignments for overlapped frames in the resegmentation step. The overlap detection module achieves state-of-the-art performance on the AMI, DIHARD, and ETAPE corpora. We apply overlap-aware resegmentation on AMI, resulting in a 20% relative DER reduction over the baseline system. While this approach is by no means an end-all solution to overlap-aware diarization, it reveals promising directions for handling overlap.", "proceedingsTitle": "ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)", "conferenceName": "ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)", "publisher": "", "place": "", "date": "May 2020", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "7114-7118", "series": "", "seriesNumber": "", "DOI": "10.1109/ICASSP40776.2020.9053096", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Overlap-Aware Diarization", "language": "", "libraryCatalog": "IEEE Xplore", "callNumber": "", "rights": "", "extra": "ISSN: 2379-190X", "tags": [ { "tag": "overlapped speech detection", "type": 1 }, { "tag": "resegmentation", "type": 1 }, { "tag": "speaker diarization", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2020-05-04T11:22:37Z", "dateModified": "2020-05-04T11:22:37Z" } }, { "key": "XL7L9UUN", "version": 786, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/XL7L9UUN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/XL7L9UUN", "type": "text/html" } }, "meta": { "creatorSummary": "Huang et al.", "parsedDate": "2020-05", "numChildren": 2 }, "data": { "key": "XL7L9UUN", "version": 786, "itemType": "conferencePaper", "title": "Speaker Diarization with Region Proposal Network", "creators": [ { "creatorType": "author", "firstName": "Zili", "lastName": "Huang" }, { "creatorType": "author", "firstName": "Shinji", "lastName": "Watanabe" }, { "creatorType": "author", "firstName": "Yusuke", "lastName": "Fujita" }, { "creatorType": "author", "firstName": "Paola", "lastName": "García" }, { "creatorType": "author", "firstName": "Yiwen", "lastName": "Shao" }, { "creatorType": "author", "firstName": "Daniel", "lastName": "Povey" }, { "creatorType": "author", "firstName": "Sanjeev", "lastName": "Khudanpur" } ], "abstractNote": "Speaker diarization is an important pre-processing step for many speech applications, and it aims to solve the \"who spoke when\" problem. Although the standard diarization systems can achieve satisfactory results in various scenarios, they are composed of several independently-optimized modules and cannot deal with the overlapped speech. In this paper, we propose a novel speaker diarization method: Region Proposal Network based Speaker Diarization (RPNSD). In this method, a neural network generates overlapped speech segment proposals, and compute their speaker embeddings at the same time. Compared with standard diarization systems, RPNSD has a shorter pipeline and can handle the overlapped speech. Experimental results on three diarization datasets reveal that RPNSD achieves remarkable improvements over the state-of-the-art x-vector baseline.", "proceedingsTitle": "ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)", "conferenceName": "ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)", "publisher": "", "place": "", "date": "May 2020", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "6514-6518", "series": "", "seriesNumber": "", "DOI": "10.1109/ICASSP40776.2020.9053760", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "IEEE Xplore", "callNumber": "", "rights": "", "extra": "ISSN: 2379-190X", "tags": [ { "tag": "Faster R-CNN", "type": 1 }, { "tag": "end-to-end", "type": 1 }, { "tag": "neural network", "type": 1 }, { "tag": "region proposal network", "type": 1 }, { "tag": "speaker diarization", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2020-05-04T11:22:19Z", "dateModified": "2020-05-04T11:22:19Z" } }, { "key": "X4LBADK5", "version": 784, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/X4LBADK5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/X4LBADK5", "type": "text/html" } }, "meta": { "creatorSummary": "Harris and Wasilewski", "parsedDate": "2004", "numChildren": 1 }, "data": { "key": "X4LBADK5", "version": 784, "itemType": "journalArticle", "title": "Indigeneity, an alternative worldview: four R's (relationship, responsibility, reciprocity, redistribution) vs. two P's (power and profit). Sharing the journey towards conscious evolution", "creators": [ { "creatorType": "author", "firstName": "La Donna", "lastName": "Harris" }, { "creatorType": "author", "firstName": "Jacqueline", "lastName": "Wasilewski" } ], "abstractNote": "La Donna Harris, founder of Americans for Indian Opportunity (AIO), discusses the two-decade-long collaboration between AIO and Alexander Christakis, President of ISSS, and other systems scientists. Structured dialogue processes have provided culturally resonant means through which Indigenous peoples have been able to identify and articulate their core values to broader audiences, especially the four R's (Relationship, Responsibility, Reciprocity and Redistribution). These Four R's form the core of an emerging concept, Indigeneity. The dynamic inclusivity of this value cluster has much to contribute to global discourse as we go about the task of constructing global agoras, the dialogic spaces of optimal mutual learning of the 21st century. Copyright © 2004 John Wiley & Sons, Ltd.", "publicationTitle": "Systems Research and Behavioral Science", "publisher": "", "place": "", "date": "2004", "volume": "21", "issue": "5", "section": "", "partNumber": "", "partTitle": "", "pages": "489-503", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1002/sres.631", "citationKey": "", "url": "https://onlinelibrary.wiley.com/doi/abs/10.1002/sres.631", "accessDate": "2020-04-18T01:11:28Z", "PMID": "", "PMCID": "", "ISSN": "1099-1743", "archive": "", "archiveLocation": "", "shortTitle": "Indigeneity, an alternative worldview", "language": "en", "libraryCatalog": "Wiley Online Library", "callNumber": "", "rights": "Copyright © 2004 John Wiley & Sons, Ltd.", "extra": "_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1002/sres.631", "tags": [ { "tag": "Advancement of Global Indigeneity (AGI)", "type": 1 }, { "tag": "Advancement of Maori Opportunity (AMO)", "type": 1 }, { "tag": "Americans for Indian Opportunity (AIO)", "type": 1 }, { "tag": "CogniscopeTM", "type": 1 }, { "tag": "ILISTM", "type": 1 }, { "tag": "Indigeneity", "type": 1 }, { "tag": "Interactive Management", "type": 1 }, { "tag": "Maoris", "type": 1 }, { "tag": "Native Americans", "type": 1 }, { "tag": "core values", "type": 1 }, { "tag": "dynamic inclusivity", "type": 1 }, { "tag": "globalization", "type": 1 }, { "tag": "governance", "type": 1 }, { "tag": "leadership", "type": 1 }, { "tag": "structured dialogue processes", "type": 1 }, { "tag": "the four R's", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2020-04-18T01:11:28Z", "dateModified": "2020-04-18T01:11:28Z" } }, { "key": "FHICIHUT", "version": 782, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/FHICIHUT", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/FHICIHUT", "type": "text/html" } }, "meta": { "creatorSummary": "Hartshorne et al.", "parsedDate": "2019-08-01", "numChildren": 1 }, "data": { "key": "FHICIHUT", "version": 782, "itemType": "journalArticle", "title": "A thousand studies for the price of one: Accelerating psychological science with Pushkin", "creators": [ { "creatorType": "author", "firstName": "Joshua K.", "lastName": "Hartshorne" }, { "creatorType": "author", "firstName": "Joshua R.", "lastName": "de Leeuw" }, { "creatorType": "author", "firstName": "Noah D.", "lastName": "Goodman" }, { "creatorType": "author", "firstName": "Mariela", "lastName": "Jennings" }, { "creatorType": "author", "firstName": "Timothy J.", "lastName": "O’Donnell" } ], "abstractNote": "Half of the world’s population has internet access. In principle, researchers are no longer limited to subjects they can recruit into the laboratory. Any study that can be run on a computer or mobile device can be run with nearly any demographic anywhere in the world, and in large numbers. This has allowed scientists to effectively run hundreds of experiments at once. Despite their transformative power, such studies remain rare for practical reasons: the need for sophisticated software, the difficulty of recruiting so many subjects, and a lack of research paradigms that make effective use of their large amounts of data, due to such realities as that they require sophisticated software in order to run effectively. We present Pushkin: an open-source platform for designing and conducting massive experiments over the internet. Pushkin allows for a wide range of behavioral paradigms, through integration with the intuitive and flexible jsPsych experiment engine. It also addresses the basic technical challenges associated with massive, worldwide studies, including auto-scaling, extensibility, machine-assisted experimental design, multisession studies, and data security.", "publicationTitle": "Behavior Research Methods", "publisher": "", "place": "", "date": "2019-08-01", "volume": "51", "issue": "4", "section": "", "partNumber": "", "partTitle": "", "pages": "1782-1803", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Behav Res", "DOI": "10.3758/s13428-018-1155-z", "citationKey": "", "url": "https://doi.org/10.3758/s13428-018-1155-z", "accessDate": "2020-04-06T09:45:04Z", "PMID": "", "PMCID": "", "ISSN": "1554-3528", "archive": "", "archiveLocation": "", "shortTitle": "A thousand studies for the price of one", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2020-04-06T09:45:03Z", "dateModified": "2020-04-06T09:45:03Z" } }, { "key": "DDMGCJ7J", "version": 781, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/DDMGCJ7J", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/DDMGCJ7J", "type": "text/html" } }, "meta": { "creatorSummary": "Shahaf et al.", "parsedDate": "2015-08-10", "numChildren": 0 }, "data": { "key": "DDMGCJ7J", "version": 781, "itemType": "conferencePaper", "title": "Inside Jokes: Identifying Humorous Cartoon Captions", "creators": [ { "creatorType": "author", "firstName": "Dafna", "lastName": "Shahaf" }, { "creatorType": "author", "firstName": "Eric", "lastName": "Horvitz" }, { "creatorType": "author", "firstName": "Robert", "lastName": "Mankoff" } ], "abstractNote": "Humor is an integral aspect of the human experience. Motivated by the prospect of creating computational models of humor, we study the influence of the language of cartoon captions on the perceived humorousness of the cartoons. Our studies are based on a large corpus of crowdsourced cartoon captions that were submitted to a contest hosted by the New Yorker. Having access to thousands of captions submitted for the same image allows us to analyze the breadth of responses of people to the same visual stimulus. We first describe how we acquire judgments about the humorousness of different captions. Then, we detail the construction of a corpus where captions deemed funnier are paired with less-funny captions for the same cartoon. We analyze the caption pairs and find significant differences between the funnier and less-funny captions. Next, we build a classifier to identify funnier captions automatically. Given two captions and a cartoon, our classifier picks the funnier one 69% of the time for captions hinging on the same joke, and 64% of the time for any pair of captions. Finally, we use the classifier to find the best captions and study how its predictions could be used to significantly reduce the load on the cartoon contest's judges.", "proceedingsTitle": "Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining", "conferenceName": "", "publisher": "Association for Computing Machinery", "place": "Sydney, NSW, Australia", "date": "August 10, 2015", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1065–1074", "series": "KDD '15", "seriesNumber": "", "DOI": "10.1145/2783258.2783388", "ISBN": "978-1-4503-3664-2", "citationKey": "", "url": "https://doi.org/10.1145/2783258.2783388", "accessDate": "2020-03-01", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "Inside Jokes", "language": "", "libraryCatalog": "ACM Digital Library", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "cartoon", "type": 1 }, { "tag": "cartoon caption", "type": 1 }, { "tag": "humor", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2020-03-01T12:56:11Z", "dateModified": "2020-03-01T12:56:11Z" } }, { "key": "2M629XYX", "version": 779, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/2M629XYX", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/2M629XYX", "type": "text/html" } }, "meta": { "creatorSummary": "Phillips et al.", "parsedDate": "2018-03-01", "numChildren": 2 }, "data": { "key": "2M629XYX", "version": 779, "itemType": "journalArticle", "title": "Revealing the ecological content of long-duration audio-recordings of the environment through clustering and visualisation", "creators": [ { "creatorType": "author", "firstName": "Yvonne F.", "lastName": "Phillips" }, { "creatorType": "author", "firstName": "Michael", "lastName": "Towsey" }, { "creatorType": "author", "firstName": "Paul", "lastName": "Roe" } ], "abstractNote": "Audio recordings of the environment are an increasingly important technique to monitor biodiversity and ecosystem function. While the acquisition of long-duration recordings is becoming easier and cheaper, the analysis and interpretation of that audio remains a significant research area. The issue addressed in this paper is the automated reduction of environmental audio data to facilitate ecological investigations. We describe a method that first reduces environmental audio to vectors of acoustic indices, which are then clustered. This can reduce the audio data by six to eight orders of magnitude yet retain useful ecological information. We describe techniques to visualise sequences of cluster occurrence (using for example, diel plots, rose plots) that assist interpretation of environmental audio. Colour coding acoustic clusters allows months and years of audio data to be visualised in a single image. These techniques are useful in identifying and indexing the contents of long-duration audio recordings. They could also play an important role in monitoring long-term changes in species abundance brought about by habitat degradation and/or restoration.", "publicationTitle": "PLoS ONE", "publisher": "", "place": "", "date": "2018-3-1", "volume": "13", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "PLoS One", "DOI": "10.1371/journal.pone.0193345", "citationKey": "", "url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5832236/", "accessDate": "2020-01-24T15:32:48Z", "PMID": "", "PMCID": "", "ISSN": "1932-6203", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "PubMed Central", "callNumber": "", "rights": "", "extra": "PMID: 29494629\nPMCID: PMC5832236", "tags": [], "collections": [], "relations": {}, "dateAdded": "2020-01-24T15:32:48Z", "dateModified": "2020-01-24T15:32:48Z" } }, { "key": "3L4RBD2F", "version": 777, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/3L4RBD2F", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/3L4RBD2F", "type": "text/html" } }, "meta": { "creatorSummary": "Mandel Michael I. et al.", "parsedDate": "2019-12-26", "numChildren": 1 }, "data": { "key": "3L4RBD2F", "version": 777, "itemType": "journalArticle", "title": "The Bubble Noise Technique for Speech Perception Research", "creators": [ { "creatorType": "author", "name": "Mandel Michael I." }, { "creatorType": "author", "name": "Grover Vikas" }, { "creatorType": "author", "name": "Zhao Mengxuan" }, { "creatorType": "author", "name": "Choi Jiyoung" }, { "creatorType": "author", "name": "Shafer Valerie L." } ], "abstractNote": "Purpose\n The “bubble noise” technique has recently been introduced as a method to identify\n the regions in time–frequency maps (i.e., spectrograms) of speech that are especially\n important for listeners in speech recognition. This technique identifies regions of\n “importance” that are specific to the speech stimulus and the listener, thus permitting\n these regions to be compared across different listener groups. For example, in cross-linguistic\n and second-language (L2) speech perception, this method identifies differences in\n regions of importance in accomplishing decisions of phoneme category membership. This\n research note describes the application of bubble noise to the study of language learning\n for 3 different language pairs: Hindi English bilinguals' perception of the /v/–/w/\n contrast in American English, native English speakers' perception of the tense/lax\n contrast for Korean fricatives and affricates, and native English speakers' perception\n of Mandarin lexical tone.\n \n \n Conclusion\n We demonstrate that this technique provides insight on what information in the speech\n signal is important for native/first-language listeners compared to nonnative/L2 listeners.\n Furthermore, the method can be used to examine whether L2 speech perception training\n is effective in bringing the listener's attention to the important cues.", "publicationTitle": "Perspectives of the ASHA Special Interest Groups", "publisher": "", "place": "", "date": "December 26, 2019", "volume": "4", "issue": "6", "section": "", "partNumber": "", "partTitle": "", "pages": "1653-1666", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Perspectives of the ASHA Special Interest Groups", "DOI": "10.1044/2019_PERS-19-00058", "citationKey": "", "url": "https://pubs.asha.org/doi/10.1044/2019_PERS-19-00058", "accessDate": "2020-01-09T03:43:26Z", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "pubs.asha.org (Atypon)", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2020-01-09T03:43:26Z", "dateModified": "2020-01-09T03:43:26Z" } }, { "key": "6UJSJPE2", "version": 773, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/6UJSJPE2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/6UJSJPE2", "type": "text/html" } }, "meta": { "numChildren": 0 }, "data": { "key": "6UJSJPE2", "version": 773, "itemType": "webpage", "title": "WaveTract: A hybrid generative model for speech synthesis - IEEE Conference Publication", "creators": [], "abstractNote": "", "websiteTitle": "", "websiteType": "", "date": "", "publisher": "", "place": "", "DOI": "", "citationKey": "", "url": "https://ieeexplore.ieee.org/abstract/document/8906280", "accessDate": "2019-11-26T20:02:54Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2019-11-26T20:02:38Z", "dateModified": "2019-11-26T20:02:38Z" } }, { "key": "6X5H5JDD", "version": 771, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/6X5H5JDD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/6X5H5JDD", "type": "text/html" } }, "meta": { "creatorSummary": "Farina and Negro", "parsedDate": "2015-01", "numChildren": 1 }, "data": { "key": "6X5H5JDD", "version": 771, "itemType": "journalArticle", "title": "Common Synaptic Input to Motor Neurons, Motor Unit Synchronization, and Force Control", "creators": [ { "creatorType": "author", "firstName": "Dario", "lastName": "Farina" }, { "creatorType": "author", "firstName": "Francesco", "lastName": "Negro" } ], "abstractNote": "In considering the role of common synaptic input to motor neurons in force control, we hypothesize that the effective neural drive to muscle replicates the common input and is, thus, the main determinant of force production. Such a perspective argues against a significant role for motor unit synchronization in force control.", "publicationTitle": "Exercise and Sport Sciences Reviews", "publisher": "", "place": "", "date": "January 2015", "volume": "43", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "23", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10.1249/JES.0000000000000032", "citationKey": "", "url": "https://journals.lww.com/acsm-essr/fulltext/2015/01000/Common_Synaptic_Input_to_Motor_Neurons,_Motor_Unit.6.aspx", "accessDate": "2019-11-18T19:40:44Z", "PMID": "", "PMCID": "", "ISSN": "0091-6331", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en-US", "libraryCatalog": "journals.lww.com", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2019-11-18T19:40:44Z", "dateModified": "2019-11-18T19:40:44Z" } }, { "key": "5JVEYC45", "version": 768, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/5JVEYC45", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/5JVEYC45", "type": "text/html" } }, "meta": { "creatorSummary": "Farina et al.", "parsedDate": "2014-10-02", "numChildren": 2 }, "data": { "key": "5JVEYC45", "version": 768, "itemType": "journalArticle", "title": "The extraction of neural strategies from the surface EMG: an update", "creators": [ { "creatorType": "author", "firstName": "Dario", "lastName": "Farina" }, { "creatorType": "author", "firstName": "Roberto", "lastName": "Merletti" }, { "creatorType": "author", "firstName": "Roger M.", "lastName": "Enoka" } ], "abstractNote": "A surface EMG signal represents the linear transformation of motor neuron discharge times by the compound action potentials of the innervated muscle fibers and is often used as a source of information about neural activation of muscle. However, retrieving the embedded neural code from a surface EMG signal is extremely challenging. Most studies use indirect approaches in which selected features of the signal are interpreted as indicating certain characteristics of the neural code. These indirect associations are constrained by limitations that have been detailed previously (Farina D, Merletti R, Enoka RM. J Appl Physiol 96: 1486–1495, 2004) and are generally difficult to overcome. In an update on these issues, the current review extends the discussion to EMG-based coherence methods for assessing neural connectivity. We focus first on EMG amplitude cancellation, which intrinsically limits the association between EMG amplitude and the intensity of the neural activation and then discuss the limitations of coherence methods (EEG-EMG, EMG-EMG) as a way to assess the strength of the transmission of synaptic inputs into trains of motor unit action potentials. The debated influence of rectification on EMG spectral analysis and coherence measures is also discussed. Alternatively, there have been a number of attempts to identify the neural information directly by decomposing surface EMG signals into the discharge times of motor unit action potentials. The application of this approach is extremely powerful, but validation remains a central issue.", "publicationTitle": "Journal of Applied Physiology", "publisher": "", "place": "", "date": "October 2, 2014", "volume": "117", "issue": "11", "section": "", "partNumber": "", "partTitle": "", "pages": "1215-1230", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Journal of Applied Physiology", "DOI": "10.1152/japplphysiol.00162.2014", "citationKey": "", "url": "https://www.physiology.org/doi/full/10.1152/japplphysiol.00162.2014", "accessDate": "2019-11-18T18:41:30Z", "PMID": "", "PMCID": "", "ISSN": "8750-7587", "archive": "", "archiveLocation": "", "shortTitle": "The extraction of neural strategies from the surface EMG", "language": "", "libraryCatalog": "physiology.org (Atypon)", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2019-11-18T18:41:30Z", "dateModified": "2019-11-18T18:41:30Z" } }, { "key": "XWI9SFQ8", "version": 765, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/XWI9SFQ8", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/XWI9SFQ8", "type": "text/html" } }, "meta": { "creatorSummary": "Farina et al.", "parsedDate": "2016-02-17", "numChildren": 2 }, "data": { "key": "XWI9SFQ8", "version": 765, "itemType": "journalArticle", "title": "Principles of Motor Unit Physiology Evolve With Advances in Technology", "creators": [ { "creatorType": "author", "firstName": "Dario", "lastName": "Farina" }, { "creatorType": "author", "firstName": "Francesco", "lastName": "Negro" }, { "creatorType": "author", "firstName": "Silvia", "lastName": "Muceli" }, { "creatorType": "author", "firstName": "Roger M.", "lastName": "Enoka" } ], "abstractNote": "Movements are generated by the coordinated activation of motor units. Recent technological advances have made it possible to identify the concurrent activity of several tens of motor units, in contrast with much smaller samples available in classic studies. We discuss how these advances in technology have enabled the development of a population perspective of how the central nervous system controls motor unit activity and thereby the forces exerted by muscles.", "publicationTitle": "Physiology", "publisher": "", "place": "", "date": "February 17, 2016", "volume": "31", "issue": "2", "section": "", "partNumber": "", "partTitle": "", "pages": "83-94", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Physiology", "DOI": "10.1152/physiol.00040.2015", "citationKey": "", "url": "https://www.physiology.org/doi/full/10.1152/physiol.00040.2015", "accessDate": "2019-11-18T16:02:50Z", "PMID": "", "PMCID": "", "ISSN": "1548-9213", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "physiology.org (Atypon)", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2019-11-18T16:03:00Z", "dateModified": "2019-11-18T16:03:00Z" } }, { "key": "XY8WENF4", "version": 764, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/XY8WENF4", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/XY8WENF4", "type": "text/html" } }, "meta": { "creatorSummary": "Xiao et al.", "parsedDate": "2017", "numChildren": 0 }, "data": { "key": "XY8WENF4", "version": 764, "itemType": "bookSection", "title": "Discriminative Beamforming with Phase-Aware Neural Networks for Speech Enhancement and Recognition", "creators": [ { "creatorType": "author", "firstName": "Xiong", "lastName": "Xiao" }, { "creatorType": "author", "firstName": "Shinji", "lastName": "Watanabe" }, { "creatorType": "author", "firstName": "Hakan", "lastName": "Erdogan" }, { "creatorType": "author", "firstName": "Michael", "lastName": "Mandel" }, { "creatorType": "author", "firstName": "Liang", "lastName": "Lu" }, { "creatorType": "author", "firstName": "John R.", "lastName": "Hershey" }, { "creatorType": "author", "firstName": "Michael L.", "lastName": "Seltzer" }, { "creatorType": "author", "firstName": "Guoguo", "lastName": "Chen" }, { "creatorType": "author", "firstName": "Yu", "lastName": "Zhang" }, { "creatorType": "author", "firstName": "Dong", "lastName": "Yu" }, { "creatorType": "editor", "firstName": "Shinji", "lastName": "Watanabe" }, { "creatorType": "editor", "firstName": "Marc", "lastName": "Delcroix" }, { "creatorType": "editor", "firstName": "Florian", "lastName": "Metze" }, { "creatorType": "editor", "firstName": "John R.", "lastName": "Hershey" } ], "abstractNote": "Speech-processing systems such as automatic speech recognition (ASR) usually consist of a large number of steps to accomplish their tasks. Due to the long processing pipeline, the processing steps are usually designed to optimize cost functions that are not directly related to the task, leading to suboptimal performance. In this chapter, we introduce a beamforming (BF) network to perform spatial filtering that is optimal for the ASR task. The BF network takes in array signals and predicts the optimal beamforming parameters in the frequency domain, assuming that the array geometry does not change. The network consists of both deterministic processing steps and trainable steps realized by neural networks and trained to minimize the cross-entropy cost function of ASR. In our experiments, the BF network is trained with both artificially generated and real microphone array signals. On the AMI meeting transcription, we found that the trained BF network produces competitive ASR results compared to traditional delay-and-sum beamforming on unseen array signals.", "bookTitle": "New Era for Robust Speech Recognition: Exploiting Deep Learning", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2017", "publisher": "Springer International Publishing", "place": "Cham", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "79-104", "ISBN": "9783319646800", "DOI": "", "citationKey": "", "url": "https://doi.org/10.1007/978-3-319-64680-0_4", "accessDate": "2019-11-18T14:16:14Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "DOI: 10.1007/978-3-319-64680-0_4", "tags": [], "collections": [], "relations": {}, "dateAdded": "2019-11-18T14:16:08Z", "dateModified": "2019-11-18T14:16:08Z" } }, { "key": "ZG28LL5D", "version": 763, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/ZG28LL5D", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/ZG28LL5D", "type": "text/html" } }, "meta": { "creatorSummary": "Mandel and Barker", "parsedDate": "2017", "numChildren": 0 }, "data": { "key": "ZG28LL5D", "version": 763, "itemType": "bookSection", "title": "Multichannel Spatial Clustering Using Model-Based Source Separation", "creators": [ { "creatorType": "author", "firstName": "Michael I.", "lastName": "Mandel" }, { "creatorType": "author", "firstName": "Jon P.", "lastName": "Barker" }, { "creatorType": "editor", "firstName": "Shinji", "lastName": "Watanabe" }, { "creatorType": "editor", "firstName": "Marc", "lastName": "Delcroix" }, { "creatorType": "editor", "firstName": "Florian", "lastName": "Metze" }, { "creatorType": "editor", "firstName": "John R.", "lastName": "Hershey" } ], "abstractNote": "Recent automatic speech recognition results are quite good when the training data is matched to the test data, but much worse when they differ in some important regard, like the number and arrangement of microphones or the reverberation and noise conditions. Because these configurations are difficult to predict a priori and difficult to exhaustively train over, the use of unsupervised spatial-clustering methods is attractive. Such methods separate sources using differences in spatial characteristics, but do not need to fully model the spatial configuration of the acoustic scene. This chapter will discuss several approaches to unsupervised spatial clustering, with a focus on model-based expectation maximization source separation and localization (MESSL). It will discuss the basic two-microphone version of this model, which clusters spectrogram points based on the relative differences in phase and level between pairs of microphones, its generalization to more than two microphones, and its use to drive minimum variance distortionless response (MVDR) beamforming. These systems are evaluated for speech enhancement as well as automatic speech recognition, for which they are able to reduce word error rates by between 9.9 and 17.1% relative over a standard delay-and-sum beamformer in mismatched train–test conditions.", "bookTitle": "New Era for Robust Speech Recognition: Exploiting Deep Learning", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2017", "publisher": "Springer International Publishing", "place": "Cham", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "51-77", "ISBN": "9783319646800", "DOI": "", "citationKey": "", "url": "https://doi.org/10.1007/978-3-319-64680-0_3", "accessDate": "2019-11-18T14:16:05Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "DOI: 10.1007/978-3-319-64680-0_3", "tags": [], "collections": [], "relations": {}, "dateAdded": "2019-11-18T14:16:00Z", "dateModified": "2019-11-18T14:16:00Z" } }, { "key": "G2L3CC7A", "version": 761, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/G2L3CC7A", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/G2L3CC7A", "type": "text/html" } }, "meta": { "creatorSummary": "Mandel et al.", "parsedDate": "2018", "numChildren": 1 }, "data": { "key": "G2L3CC7A", "version": 761, "itemType": "bookSection", "title": "Multichannel Clustering and Classification Approaches", "creators": [ { "creatorType": "author", "firstName": "Michael I.", "lastName": "Mandel" }, { "creatorType": "author", "firstName": "Shoko", "lastName": "Araki" }, { "creatorType": "author", "firstName": "Tomohiro", "lastName": "Nakatani" } ], "abstractNote": "Time-frequency masks provide a powerful framework for source separation. In the multichannel setting, these masks can be constructed using the spatial characteristics of the sources and the observations in addition to their time-frequency characteristics. This chapter describes clustering and classification methods for doing so. Clustering methods group together time-frequency bins with similar characteristics. Clustering methods can be further divided into narrowband and wideband approaches, depending on whether the separation is coordinated across frequency. Classification methods predict source labels for time-frequency bins based on exposure to related training data. The chapter also discusses the estimation of the number of sources involved in a mixture, as well as methods for performing spatial filtering based on masks.", "bookTitle": "Audio Source Separation and Speech Enhancement", "series": "", "seriesNumber": "", "volume": "", "numberOfVolumes": "", "edition": "", "date": "2018", "publisher": "John Wiley & Sons, Ltd", "place": "", "originalDate": "", "originalPublisher": "", "originalPlace": "", "format": "", "pages": "235-261", "ISBN": "9781119279860", "DOI": "", "citationKey": "", "url": "https://onlinelibrary.wiley.com/doi/abs/10.1002/9781119279860.ch12", "accessDate": "2019-11-18T14:15:49Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Wiley Online Library", "callNumber": "", "rights": "", "extra": "DOI: 10.1002/9781119279860.ch12", "tags": [ { "tag": "DUET", "type": 1 }, { "tag": "MESSL", "type": 1 }, { "tag": "mask-based beamforming", "type": 1 }, { "tag": "multichannel classification", "type": 1 }, { "tag": "multichannel clustering", "type": 1 }, { "tag": "source number estimation", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2019-11-18T14:15:44Z", "dateModified": "2019-11-18T14:15:44Z" } }, { "key": "2GTRMQFC", "version": 774, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/2GTRMQFC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/2GTRMQFC", "type": "text/html" } }, "meta": { "creatorSummary": "Kahl et al.", "parsedDate": "2019", "numChildren": 1 }, "data": { "key": "2GTRMQFC", "version": 774, "itemType": "journalArticle", "title": "A Baseline for Large-Scale Bird Species Identification in Field Recordings", "creators": [ { "creatorType": "author", "firstName": "Stefan", "lastName": "Kahl" }, { "creatorType": "author", "firstName": "Thomas", "lastName": "Wilhelm-Stein" }, { "creatorType": "author", "firstName": "Holger", "lastName": "Klinck" }, { "creatorType": "author", "firstName": "Danny", "lastName": "Kowerko" }, { "creatorType": "author", "firstName": "Maximilian", "lastName": "Eibl" } ], "abstractNote": "The LifeCLEF bird identifcation task poses a difficult challenge in the domain of acoustic event classification. Deep learning techniques have greatly impacted the field of bird sound recognition in recent years. We discuss our attempt of large-scale bird species identification using the 2018 BirdCLEF baseline system.", "publicationTitle": "", "publisher": "", "place": "", "date": "2019", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "4", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Zotero", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "⛔ No DOI found" } ], "collections": [], "relations": {}, "dateAdded": "2019-11-01T01:07:11Z", "dateModified": "2019-11-04T22:01:40Z" } }, { "key": "Y7ITXZP5", "version": 759, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/Y7ITXZP5", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/Y7ITXZP5", "type": "text/html" } }, "meta": { "creatorSummary": "Steele et al.", "parsedDate": "2012", "numChildren": 1 }, "data": { "key": "Y7ITXZP5", "version": 759, "itemType": "journalArticle", "title": "Constructing ideal soundscapes: a practical study on closing the gaps between soundscape studies and urban design", "creators": [ { "creatorType": "author", "firstName": "Daniel", "lastName": "Steele" }, { "creatorType": "author", "firstName": "Nik", "lastName": "Luka" }, { "creatorType": "author", "firstName": "Catherine", "lastName": "Guastavino" } ], "abstractNote": "", "publicationTitle": "", "publisher": "", "place": "", "date": "2012", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "7", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10/ggb9zk", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Zotero", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2019-11-01T19:43:51Z", "dateModified": "2019-11-01T19:43:52Z" } }, { "key": "S8WPSLEJ", "version": 756, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/S8WPSLEJ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/S8WPSLEJ", "type": "text/html" } }, "meta": { "creatorSummary": "Axelsson et al.", "parsedDate": "2019", "numChildren": 0 }, "data": { "key": "S8WPSLEJ", "version": 756, "itemType": "journalArticle", "title": "Editorial: Soundscape Assessment", "creators": [ { "creatorType": "author", "firstName": "Östen", "lastName": "Axelsson" }, { "creatorType": "author", "firstName": "Catherine", "lastName": "Guastavino" }, { "creatorType": "author", "firstName": "Sarah R.", "lastName": "Payne" } ], "abstractNote": "Editorial: Soundscape Assessment", "publicationTitle": "Frontiers in Psychology", "publisher": "", "place": "", "date": "2019", "volume": "10", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "Front. Psychol.", "DOI": "10.3389/fpsyg.2019.02514", "citationKey": "", "url": "https://www.frontiersin.org/articles/10.3389/fpsyg.2019.02514/full", "accessDate": "2019-11-01T19:04:42Z", "PMID": "", "PMCID": "", "ISSN": "1664-1078", "archive": "", "archiveLocation": "", "shortTitle": "Editorial", "language": "English", "libraryCatalog": "Frontiers", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Perception", "type": 1 }, { "tag": "Standardisation", "type": 1 }, { "tag": "assessment", "type": 1 }, { "tag": "methodology", "type": 1 }, { "tag": "soundscape", "type": 1 }, { "tag": "⚠️ Invalid DOI" } ], "collections": [], "relations": {}, "dateAdded": "2019-11-01T19:04:42Z", "dateModified": "2019-11-01T19:04:45Z" } }, { "key": "C5BSQVZA", "version": 754, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/C5BSQVZA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/C5BSQVZA", "type": "text/html" } }, "meta": { "creatorSummary": "Lasseck", "parsedDate": "2019", "numChildren": 1 }, "data": { "key": "C5BSQVZA", "version": 754, "itemType": "journalArticle", "title": "Bird Species Identification in Soundscapes", "creators": [ { "creatorType": "author", "firstName": "Mario", "lastName": "Lasseck" } ], "abstractNote": "This paper presents deep learning techniques for audio-based bird identification in soundscapes. Deep Convolutional Neural Networks are trained to classify 659 species. Different data augmentation techniques are applied to prevent overfitting and improve model accuracy and generalization. The proposed approach is evaluated in the BirdCLEF 2019 campaign and provides the best system to identify bird species in wildlife monitoring recordings. With an ensemble of different single- and multi-label classification models it obtains a classification mean average precision (c-mAP) of 35.6 % and a retrieval mean average precision (r-mAP) of 74.6 % on the official BirdCLEF test set. In terms of classification precision, single model performance surpasses previous stateof-the-art by more than 20 %.", "publicationTitle": "", "publisher": "", "place": "", "date": "2019", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "10", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Zotero", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "⛔ No DOI found" } ], "collections": [], "relations": {}, "dateAdded": "2019-11-01T01:01:09Z", "dateModified": "2019-11-01T01:01:26Z" } }, { "key": "X572EIAG", "version": 753, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/X572EIAG", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/X572EIAG", "type": "text/html" } }, "meta": { "creatorSummary": "Kahl et al.", "parsedDate": "2019", "numChildren": 1 }, "data": { "key": "X572EIAG", "version": 753, "itemType": "journalArticle", "title": "Overview of BirdCLEF 2019: Large-Scale Bird Recognition in Soundscapes", "creators": [ { "creatorType": "author", "firstName": "Stefan", "lastName": "Kahl" }, { "creatorType": "author", "firstName": "Fabian-Robert", "lastName": "Stoter" }, { "creatorType": "author", "firstName": "Herve", "lastName": "Goeau" }, { "creatorType": "author", "firstName": "Herve", "lastName": "Glotin" }, { "creatorType": "author", "firstName": "Willem-Pier", "lastName": "Vellinga" }, { "creatorType": "author", "firstName": "Alexis", "lastName": "Joly" } ], "abstractNote": "The BirdCLEF challenge—as part of the 2019 LifeCLEF Lab [7]—offers a large-scale proving ground for system-oriented evaluation of bird species identification based on audio recordings. The challenge uses data collected through Xeno-canto, the worldwide community of bird sound recordists. This ensures that BirdCLEF is close to the conditions of real-world application, in particular with regard to the number of species in the training set (659). In 2019, the challenge was focused on the difficult task of recognizing all birds vocalizing in omni-directional soundscape recordings. Therefore, the dataset of the previous year was extended with more than 350 hours of manually annotated soundscapes that were recorded using 30 field recorders in Ithaca (NY, USA). This paper describes the methodology of the conducted evaluation as well as the synthesis of the main results and lessons learned.", "publicationTitle": "", "publisher": "", "place": "", "date": "2019", "volume": "", "issue": "", "section": "", "partNumber": "", "partTitle": "", "pages": "9", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "en", "libraryCatalog": "Zotero", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "⛔ No DOI found" } ], "collections": [], "relations": {}, "dateAdded": "2019-11-01T01:00:16Z", "dateModified": "2019-11-01T01:00:49Z" } }, { "key": "G7RLRVTK", "version": 751, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/G7RLRVTK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/G7RLRVTK", "type": "text/html" } }, "meta": { "creatorSummary": "Ellis et al.", "parsedDate": "2011-05", "numChildren": 1 }, "data": { "key": "G7RLRVTK", "version": 751, "itemType": "conferencePaper", "title": "Classifying soundtracks with audio texture features", "creators": [ { "creatorType": "author", "firstName": "Daniel P. W.", "lastName": "Ellis" }, { "creatorType": "author", "firstName": "Xiaohong", "lastName": "Zeng" }, { "creatorType": "author", "firstName": "Josh H.", "lastName": "McDermott" } ], "abstractNote": "Sound textures may be defined as sounds whose character depends on statistical properties as much as the specific details of each individually-perceived event. Recent work has devised a set of statistics that, when synthetically imposed, allow listeners to identify a wide range of environmental sound textures. In this work, we investigate using these statistics for automatic classification of a set of environmental sound classes defined over a set of web videos depicting \"multimedia events\". We show that the texture statistics perform as well as our best conventional statistics (based on MFCC covariance). We further examine the relative contributions of the different statistics, showing the importance of modulation spectra and cross-band envelope correlations.", "proceedingsTitle": "2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)", "conferenceName": "2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)", "publisher": "", "place": "", "date": "May 2011", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "5880-5883", "series": "", "seriesNumber": "", "DOI": "10/cmh958", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "IEEE Xplore", "callNumber": "", "rights": "", "extra": "ISSN: 2379-190X, 1520-6149, 1520-6149", "tags": [ { "tag": "Accuracy", "type": 1 }, { "tag": "Correlation", "type": 1 }, { "tag": "Mel frequency cepstral coefficient", "type": 1 }, { "tag": "Modulation", "type": 1 }, { "tag": "Sound textures", "type": 1 }, { "tag": "Speech", "type": 1 }, { "tag": "Support vector machines", "type": 1 }, { "tag": "Videos", "type": 1 }, { "tag": "audio signal processing", "type": 1 }, { "tag": "audio texture features", "type": 1 }, { "tag": "cross-band envelope correlations", "type": 1 }, { "tag": "environmental sound", "type": 1 }, { "tag": "environmental sound classes", "type": 1 }, { "tag": "modulation spectra", "type": 1 }, { "tag": "soundtrack classification", "type": 1 }, { "tag": "soundtracks", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2019-10-22T00:51:38Z", "dateModified": "2019-10-22T00:51:39Z" } }, { "key": "JQNUTH6M", "version": 751, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/JQNUTH6M", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/JQNUTH6M", "type": "text/html" } }, "meta": { "creatorSummary": "Liston and Hiemstra", "parsedDate": "2011-06-20", "numChildren": 2 }, "data": { "key": "JQNUTH6M", "version": 751, "itemType": "journalArticle", "title": "The Changing Cryosphere: Pan-Arctic Snow Trends (1979–2009)", "creators": [ { "creatorType": "author", "firstName": "Glen E.", "lastName": "Liston" }, { "creatorType": "author", "firstName": "Christopher A.", "lastName": "Hiemstra" } ], "abstractNote": "Arctic snow presence, absence, properties, and water amount are key components of Earth’s changing climate system that incur far-reaching physical and biological ramifications. Recent dataset and modeling developments permit relatively high-resolution (10-km horizontal grid; 3-h time step) pan-Arctic snow estimates for 1979–2009. Using MicroMet and SnowModel in conjunction with land cover, topography, and 30 years of the NASA Modern-Era Retrospective Analysis for Research and Applications (MERRA) atmospheric reanalysis data, a distributed snow-related dataset was created including air temperature, snow precipitation, snow-season timing and length, maximum snow water equivalent (SWE) depth, average snow density, snow sublimation, and rain-on-snow events. Regional variability is a dominant feature of the modeled snow-property trends. Both positive and negative regional trends are distributed throughout the pan-Arctic domain, featuring, for example, spatially distinct areas of increasing and decreasing SWE or snow season length. In spite of strong regional variability, the data clearly show a general snow decrease throughout the Arctic: maximum winter SWE has decreased, snow-cover onset is later, the snow-free date in spring is earlier, and snow-cover duration has decreased. The domain-averaged air temperature trend when snow was on the ground was 0.17°C decade−1 with minimum and maximum regional trends of −0.55° and 0.78°C decade−1, respectively. The trends for total number of snow days in a year averaged −2.49 days decade−1 with minimum and maximum regional trends of −17.21 and 7.19 days decade−1, respectively. The average trend for peak SWE in a snow season was −0.17 cm decade−1 with minimum and maximum regional trends of −2.50 and 5.70 cm decade−1, respectively.", "publicationTitle": "Journal of Climate", "publisher": "", "place": "", "date": "June 20, 2011", "volume": "24", "issue": "21", "section": "", "partNumber": "", "partTitle": "", "pages": "5691-5712", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "J. Climate", "DOI": "10/d3krzc", "citationKey": "", "url": "https://journals.ametsoc.org/doi/full/10.1175/JCLI-D-11-00081.1", "accessDate": "2019-10-22T00:50:28Z", "PMID": "", "PMCID": "", "ISSN": "0894-8755", "archive": "", "archiveLocation": "", "shortTitle": "The Changing Cryosphere", "language": "", "libraryCatalog": "journals.ametsoc.org (Atypon)", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2019-10-22T00:50:28Z", "dateModified": "2019-10-22T00:50:29Z" } }, { "key": "8PVBTRCW", "version": 749, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/8PVBTRCW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/8PVBTRCW", "type": "text/html" } }, "meta": { "creatorSummary": "Callaghan et al.", "parsedDate": "2011-12-01", "numChildren": 1 }, "data": { "key": "8PVBTRCW", "version": 749, "itemType": "journalArticle", "title": "The Changing Face of Arctic Snow Cover: A Synthesis of Observed and Projected Changes", "creators": [ { "creatorType": "author", "firstName": "Terry V.", "lastName": "Callaghan" }, { "creatorType": "author", "firstName": "Margareta", "lastName": "Johansson" }, { "creatorType": "author", "firstName": "Ross D.", "lastName": "Brown" }, { "creatorType": "author", "firstName": "Pavel Ya.", "lastName": "Groisman" }, { "creatorType": "author", "firstName": "Niklas", "lastName": "Labba" }, { "creatorType": "author", "firstName": "Vladimir", "lastName": "Radionov" }, { "creatorType": "author", "firstName": "Roger G.", "lastName": "Barry" }, { "creatorType": "author", "firstName": "Olga N.", "lastName": "Bulygina" }, { "creatorType": "author", "firstName": "Richard L. H.", "lastName": "Essery" }, { "creatorType": "author", "firstName": "D. M.", "lastName": "Frolov" }, { "creatorType": "author", "firstName": "Vladimir N.", "lastName": "Golubev" }, { "creatorType": "author", "firstName": "Thomas C.", "lastName": "Grenfell" }, { "creatorType": "author", "firstName": "Marina N.", "lastName": "Petrushina" }, { "creatorType": "author", "firstName": "Vyacheslav N.", "lastName": "Razuvaev" }, { "creatorType": "author", "firstName": "David A.", "lastName": "Robinson" }, { "creatorType": "author", "firstName": "Peter", "lastName": "Romanov" }, { "creatorType": "author", "firstName": "Drew", "lastName": "Shindell" }, { "creatorType": "author", "firstName": "Andrey B.", "lastName": "Shmakin" }, { "creatorType": "author", "firstName": "Sergey A.", "lastName": "Sokratov" }, { "creatorType": "author", "firstName": "Stephen", "lastName": "Warren" }, { "creatorType": "author", "firstName": "Daquing", "lastName": "Yang" } ], "abstractNote": "Analysis of in situ and satellite data shows evidence of different regional snow cover responses to the widespread warming and increasing winter precipitation that has characterized the Arctic climate for the past 40–50 years. The largest and most rapid decreases in snow water equivalent (SWE) and snow cover duration (SCD) are observed over maritime regions of the Arctic with the highest precipitation amounts. There is also evidence of marked differences in the response of snow cover between the North American and Eurasian sectors of the Arctic, with the North American sector exhibiting decreases in snow cover and snow depth over the entire period of available in situ observations from around 1950, while widespread decreases in snow cover are not apparent over Eurasia until after around 1980. However, snow depths are increasing in many regions of Eurasia. Warming and more frequent winter thaws are contributing to changes in snow pack structure with important implications for land use and provision of ecosystem services. Projected changes in snow cover from Global Climate Models for the 2050 period indicate increases in maximum SWE of up to 15% over much of the Arctic, with the largest increases (15–30%) over the Siberian sector. In contrast, SCD is projected to decrease by about 10–20% over much of the Arctic, with the smallest decreases over Siberia (<10%) and the largest decreases over Alaska and northern Scandinavia (30–40%) by 2050. These projected changes will have far-reaching consequences for the climate system, human activities, hydrology, and ecology.", "publicationTitle": "AMBIO", "publisher": "", "place": "", "date": "2011-12-01", "volume": "40", "issue": "1", "section": "", "partNumber": "", "partTitle": "", "pages": "17-31", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "AMBIO", "DOI": "10/fxzgzc", "citationKey": "", "url": "https://doi.org/10.1007/s13280-011-0212-y", "accessDate": "2019-10-22T00:49:38Z", "PMID": "", "PMCID": "", "ISSN": "1654-7209", "archive": "", "archiveLocation": "", "shortTitle": "The Changing Face of Arctic Snow Cover", "language": "en", "libraryCatalog": "Springer Link", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Snow cover duration", "type": 1 }, { "tag": "Snow cover extent", "type": 1 }, { "tag": "Snow depth", "type": 1 }, { "tag": "Snow water equivalent", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2019-10-22T00:49:38Z", "dateModified": "2019-10-22T00:49:39Z" } }, { "key": "T4D635EB", "version": 747, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/T4D635EB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/T4D635EB", "type": "text/html" } }, "meta": { "creatorSummary": "Grill and Schlüter", "parsedDate": "2017-08", "numChildren": 1 }, "data": { "key": "T4D635EB", "version": 747, "itemType": "conferencePaper", "title": "Two convolutional neural networks for bird detection in audio signals", "creators": [ { "creatorType": "author", "firstName": "Thomas", "lastName": "Grill" }, { "creatorType": "author", "firstName": "Jan", "lastName": "Schlüter" } ], "abstractNote": "We present and compare two approaches to detect the presence of bird calls in audio recordings using convolutional neural networks on mel spectrograms. In a signal processing challenge using environmental recordings from three very different sources, only two of them available for supervised training, we obtained an Area Under Curve (AUC) measure of 89% on the hidden test set, higher than any other contestant. By comparing multiple variations of our systems, we find that despite very different architectures, both approaches can be tuned to perform equally well. Further improvements will likely require a radically different approach to dealing with the discrepancy between data sources.", "proceedingsTitle": "2017 25th European Signal Processing Conference (EUSIPCO)", "conferenceName": "2017 25th European Signal Processing Conference (EUSIPCO)", "publisher": "", "place": "", "date": "August 2017", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "1764-1768", "series": "", "seriesNumber": "", "DOI": "10/cj67", "ISBN": "", "citationKey": "", "url": "", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "IEEE Xplore", "callNumber": "", "rights": "", "extra": "ISSN: 2076-1465", "tags": [ { "tag": "AUC measure", "type": 1 }, { "tag": "Birds", "type": 1 }, { "tag": "Computer architecture", "type": 1 }, { "tag": "Convolution", "type": 1 }, { "tag": "Spectrogram", "type": 1 }, { "tag": "Training", "type": 1 }, { "tag": "Training data", "type": 1 }, { "tag": "area under curve measure", "type": 1 }, { "tag": "audio recording", "type": 1 }, { "tag": "audio recordings", "type": 1 }, { "tag": "audio signal processing", "type": 1 }, { "tag": "audio signals", "type": 1 }, { "tag": "bird calls", "type": 1 }, { "tag": "bird detection", "type": 1 }, { "tag": "convolutional neural networks", "type": 1 }, { "tag": "environmental recordings", "type": 1 }, { "tag": "feature extraction", "type": 1 }, { "tag": "learning (artificial intelligence)", "type": 1 }, { "tag": "mel spectrograms", "type": 1 }, { "tag": "neural nets", "type": 1 }, { "tag": "supervised training", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2019-10-22T00:48:05Z", "dateModified": "2019-10-22T00:48:05Z" } }, { "key": "V56T8TTA", "version": 745, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/V56T8TTA", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/V56T8TTA", "type": "text/html" } }, "meta": { "creatorSummary": "Stowell et al.", "parsedDate": "2019", "numChildren": 2 }, "data": { "key": "V56T8TTA", "version": 745, "itemType": "journalArticle", "title": "Automatic acoustic detection of birds through deep learning: The first Bird Audio Detection challenge", "creators": [ { "creatorType": "author", "firstName": "Dan", "lastName": "Stowell" }, { "creatorType": "author", "firstName": "Michael D.", "lastName": "Wood" }, { "creatorType": "author", "firstName": "Hanna", "lastName": "Pamuła" }, { "creatorType": "author", "firstName": "Yannis", "lastName": "Stylianou" }, { "creatorType": "author", "firstName": "Hervé", "lastName": "Glotin" } ], "abstractNote": "Assessing the presence and abundance of birds is important for monitoring specific species as well as overall ecosystem health. Many birds are most readily detected by their sounds, and thus, passive acoustic monitoring is highly appropriate. Yet acoustic monitoring is often held back by practical limitations such as the need for manual configuration, reliance on example sound libraries, low accuracy, low robustness, and limited ability to generalise to novel acoustic conditions. Here, we report outcomes from a collaborative data challenge. We present new acoustic monitoring datasets, summarise the machine learning techniques proposed by challenge teams, conduct detailed performance evaluation, and discuss how such approaches to detection can be integrated into remote monitoring projects. Multiple methods were able to attain performance of around 88% area under the receiver operating characteristic (ROC) curve (AUC), much higher performance than previous general-purpose methods. With modern machine learning, including deep learning, general-purpose acoustic bird detection can achieve very high retrieval rates in remote monitoring data, with no manual recalibration, and no pretraining of the detector for the target species or the acoustic conditions in the target environment.", "publicationTitle": "Methods in Ecology and Evolution", "publisher": "", "place": "", "date": "2019", "volume": "10", "issue": "3", "section": "", "partNumber": "", "partTitle": "", "pages": "368-380", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10/gfknhq", "citationKey": "", "url": "https://besjournals.onlinelibrary.wiley.com/doi/abs/10.1111/2041-210X.13103", "accessDate": "2019-10-22T00:45:46Z", "PMID": "", "PMCID": "", "ISSN": "2041-210X", "archive": "", "archiveLocation": "", "shortTitle": "Automatic acoustic detection of birds through deep learning", "language": "en", "libraryCatalog": "Wiley Online Library", "callNumber": "", "rights": "© 2018 The Authors. Methods in Ecology and Evolution published by John Wiley & Sons Ltd on behalf of British Ecological Society.", "extra": "", "tags": [ { "tag": "bird", "type": 1 }, { "tag": "deep learning", "type": 1 }, { "tag": "machine learning", "type": 1 }, { "tag": "passive acoustic monitoring", "type": 1 }, { "tag": "sound", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2019-10-22T00:45:46Z", "dateModified": "2019-10-22T00:45:47Z" } }, { "key": "RBN236XR", "version": 743, "library": { "type": "user", "id": 1252116, "name": "asterix77", "links": { "alternate": { "href": "https://www.zotero.org/asterix77", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/users/1252116/items/RBN236XR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/asterix77/items/RBN236XR", "type": "text/html" } }, "meta": { "creatorSummary": "Jensen and Taal", "parsedDate": "2016-11", "numChildren": 1 }, "data": { "key": "RBN236XR", "version": 743, "itemType": "journalArticle", "title": "An Algorithm for Predicting the Intelligibility of Speech Masked by Modulated Noise Maskers", "creators": [ { "creatorType": "author", "firstName": "Jesper", "lastName": "Jensen" }, { "creatorType": "author", "firstName": "Cees H.", "lastName": "Taal" } ], "abstractNote": "Intelligibility listening tests are necessary during development and evaluation of speech processing algorithms, despite the fact that they are expensive and time consuming. In this paper, we propose a monaural intelligibility prediction algorithm, which has the potential of replacing some of these listening tests. The proposed algorithm shows similarities to the short-time objective intelligibility (STOI) algorithm, but works for a larger range of input signals. In contrast to STOI, extended STOI (ESTOI) does not assume mutual independence between frequency bands. ESTOI also incorporates spectral correlation by comparing complete 400ms length spectrograms of the noisy/processed speech and the clean speech signals. As a consequence, ESTOI is also able to accurately predict the intelligibility of speech contaminated by temporally highly modulated noise sources in addition to noisy signals processed with time-frequency weighting. We show that ESTOI can be interpreted in terms of an orthogonal decomposition of short-time spectrograms into intelligibility subspaces, i.e., a ranking of spectrogram features according to their importance to intelligibility. A free MATLAB implementation of the algorithm is available for noncommercial use at http://kom.aau.dk/ jje/.", "publicationTitle": "IEEE/ACM Transactions on Audio, Speech, and Language Processing", "publisher": "", "place": "", "date": "November 2016", "volume": "24", "issue": "11", "section": "", "partNumber": "", "partTitle": "", "pages": "2009-2022", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "", "DOI": "10/f82bzt", "citationKey": "", "url": "", "accessDate": "", "PMID": "", "PMCID": "", "ISSN": "2329-9290, 2329-9304", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "", "libraryCatalog": "IEEE Xplore", "callNumber": "", "rights": "", "extra": "", "tags": [ { "tag": "Correlation", "type": 1 }, { "tag": "ESTOI", "type": 1 }, { "tag": "Indexes", "type": 1 }, { "tag": "Modulated noise sources", "type": 1 }, { "tag": "Modulation", "type": 1 }, { "tag": "Noise measurement", "type": 1 }, { "tag": "Prediction algorithms", "type": 1 }, { "tag": "Speech", "type": 1 }, { "tag": "Speech processing", "type": 1 }, { "tag": "extended STOI algorithm", "type": 1 }, { "tag": "intelligibility listening test", "type": 1 }, { "tag": "monaural intelligibility prediction algorithm", "type": 1 }, { "tag": "noise masker modulation", "type": 1 }, { "tag": "noise reduction", "type": 1 }, { "tag": "objective distortion measures", "type": 1 }, { "tag": "short-time objective intelligibility algorithm", "type": 1 }, { "tag": "short-time spectrogram orthogonal decomposition", "type": 1 }, { "tag": "spectral correlation", "type": 1 }, { "tag": "speech enhancement", "type": 1 }, { "tag": "speech intelligibility", "type": 1 }, { "tag": "speech intelligibility prediction", "type": 1 }, { "tag": "speech processing", "type": 1 }, { "tag": "speech processing algorithm", "type": 1 }, { "tag": "time-frequency analysis", "type": 1 }, { "tag": "time-frequency weighting", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2019-10-19T01:07:44Z", "dateModified": "2019-10-19T01:07:44Z" } } ]