{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T07:40:05Z","timestamp":1749973205946,"version":"3.41.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/slt.2016.7846308","type":"proceedings-article","created":{"date-parts":[[2017,2,10]],"date-time":"2017-02-10T15:58:30Z","timestamp":1486742310000},"page":"489-495","source":"Crossref","is-referenced-by-count":4,"title":["Deep learning with maximal figure-of-merit cost to advance multi-label speech attribute detection"],"prefix":"10.1109","author":[{"given":"Ivan","family":"Kukanov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ville","family":"Hautamaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sabato Marco","family":"Siniscalchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kehuang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.409839"},{"key":"ref11","first-page":"iv-869","article-title":"High-accuracy phone recognition by combining highperformance lattice generation and knowledge based rescoring","author":"siniscalchi","year":"2007","journal-title":"Proc ICASSP"},{"key":"ref12","article-title":"Boosting universal speech attributes classification with deep neural network for foreign accent characterization","author":"hautam\u00e4ki","year":"2015","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.05.001"},{"key":"ref14","first-page":"437","article-title":"Large-scale multi-label text classification - revisiting neural networks","volume":"8725","author":"nam","year":"2014","journal-title":"Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD-14) Part 2 ser Lecture Notes in Computer Science"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2006.162"},{"key":"ref16","article-title":"A literature survey on algorithms for multi-label learning","author":"sorower","year":"2010","journal-title":"Tech Rep"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1148020.1148022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854454"},{"key":"ref19","first-page":"70","article-title":"Francis katamba, an introduction to phonology","volume":"22","author":"gasiorowski","year":"1992","journal-title":"Journal of the International Phonetic Association"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743864"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"1613","DOI":"10.21437\/Eurospeech.2001-195","article-title":"Distinctive features for use in an automatic speech recognition system","author":"eide","year":"2001","journal-title":"Proc EUROSPEECH"},{"key":"ref6","first-page":"16","article-title":"A flexible stream architecture for ASR using articulatory features","author":"metze","year":"2002","journal-title":"Proc ICSLP"},{"key":"ref5","first-page":"891","article-title":"Combining articulatory and acoustic information for speech recognition in noisy and reverberant environments","author":"kirchhoff","year":"1998","journal-title":"Proc ICSLP"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2238591"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00031-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.540282"},{"key":"ref9","first-page":"1829","article-title":"Detection-based ASR in the automatic speech attribute transcription project","author":"bromberg","year":"0","journal-title":"INTER-SPEECH 2007 8th Annual Conference of the International Speech Communication Association"},{"key":"ref1","first-page":"2117","article-title":"An HMM acoustic model incorporating various additional knowledge sources","author":"sakti","year":"2007","journal-title":"Proc INTERSPEECH"},{"journal-title":"Pattern Recognition and Machine Learning","year":"2006","author":"bishop","key":"ref20"},{"journal-title":"Handbook of Neural Network Signal Processing","year":"2000","author":"hu","key":"ref22"},{"key":"ref21","first-page":"1","article-title":"A review on multi-label learning algorithms","author":"zhang","year":"2013","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref23","first-page":"895","article-title":"The OGI Multi-Language telephone speech corpus","author":"muthusamy","year":"1992","journal-title":"Proceedings of the International Conference on Spoken Language Processing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"}],"event":{"name":"2016 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2016,12,13]]},"location":"San Diego, CA","end":{"date-parts":[[2016,12,16]]}},"container-title":["2016 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7836849\/7846230\/07846308.pdf?arnumber=7846308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T07:19:38Z","timestamp":1749971978000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7846308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/slt.2016.7846308","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}