{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:48:25Z","timestamp":1729676905544,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/waspaa.2017.8169986","type":"proceedings-article","created":{"date-parts":[[2017,12,13]],"date-time":"2017-12-13T14:38:44Z","timestamp":1513175924000},"page":"16-20","source":"Crossref","is-referenced-by-count":0,"title":["Learning vocal mode classifiers from heterogeneous data sources"],"prefix":"10.1109","author":[{"given":"Zhao","family":"Shuyang","sequence":"first","affiliation":[]},{"given":"Toni","family":"Heittola","sequence":"additional","affiliation":[]},{"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"29","article-title":"The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions","author":"pearce","year":"2000","journal-title":"Sixth International Conference on Spoken Language Processing ICSLP 2000 \/ INTERSPEECH"},{"key":"ref11","first-page":"1","article-title":"Poly-phonic sound event detection using multi label deep neural networks","author":"cakir","year":"2015","journal-title":"2015 International Joint Conference on Neural Networks IJCNN"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952131"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.10.004"},{"key":"ref14","article-title":"CMU arctic databases for speech synthesis","author":"kominek","year":"2003","journal-title":"Tech report Carnegie Mellon University"},{"key":"ref15","article-title":"Quantile based histogram equalization for online applications","author":"hilger","year":"2002","journal-title":"7th International Conference on Spoken Language Processing ICSLP2002"},{"key":"ref16","article-title":"Enhanced histogram normalization in the acoustic feature space","author":"molau","year":"2002","journal-title":"7th International Conference on Spoken Language Processing ICSLP2002"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1999-57","article-title":"On combining vocal tract length normalisation and speaker adaptation for noise robust speech recognition","author":"hariharan","year":"1999","journal-title":"Sixth European Conference on Speech Communication and Technology EUROSPEECH 1999"},{"journal-title":"Neural Networks A Comprehensive Foundation","year":"1998","author":"haykin","key":"ref18"},{"journal-title":"Keras","year":"2015","author":"chollet","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198866"},{"journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE 2016) Tampere University of Technology Department of Signal Processing","year":"2016","author":"virtanen","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.845805"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857792"},{"key":"ref2","first-page":"732","article-title":"Speaker and noise independent voice activity detection","author":"germain","year":"2013","journal-title":"INTER-SPEECH 2013 14th Annual Conference of the International Speech Communication Association"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00033-8"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2495219"},{"volume":"abs 1605 2688","journal-title":"Theano A Python framework for fast computation of mathematical expressions","year":"2016","key":"ref20"},{"journal-title":"Karaoke","year":"0","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2001109"},{"key":"ref24","article-title":"Melodic characterization and similarity in a cappella flamenco cantes","author":"mora","year":"2010","journal-title":"11th International Society for Music Information Retrieval Conference"},{"key":"ref23","article-title":"MedleyDB: A multitrack dataset for annotation-intensive mir research","author":"bittner","year":"2014","journal-title":"International Society for Music Information Retrieval Conference"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0144610"}],"event":{"name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2017,10,15]]},"location":"New Paltz, NY","end":{"date-parts":[[2017,10,18]]}},"container-title":["2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8125199\/8169982\/08169986.pdf?arnumber=8169986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,10]],"date-time":"2022-08-10T08:51:56Z","timestamp":1660121516000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8169986\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/waspaa.2017.8169986","relation":{},"subject":[],"published":{"date-parts":[[2017,10]]}}}