{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:02:59Z","timestamp":1730296979375,"version":"3.28.0"},"reference-count":47,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/slt.2016.7846242","type":"proceedings-article","created":{"date-parts":[[2017,2,10]],"date-time":"2017-02-10T15:58:30Z","timestamp":1486742310000},"page":"35-42","source":"Crossref","is-referenced-by-count":3,"title":["Deep bottleneck features and sound-dependent i-vectors for simultaneous recognition of speech and environmental sounds"],"prefix":"10.1109","author":[{"given":"Sakriani","family":"Sakti","sequence":"first","affiliation":[]},{"given":"Seiji","family":"Kawanishi","sequence":"additional","affiliation":[]},{"given":"Graham","family":"Neubig","sequence":"additional","affiliation":[]},{"given":"Koichiro","family":"Yoshino","sequence":"additional","affiliation":[]},{"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.1109\/ICASSP.2013.6639012"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/ICASSP.2015.7178814"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1006\/csla.1998.0043"},{"key":"ref32","first-page":"1137","article-title":"A compact model for speaker adaptive training","author":"schwartz","year":"1996","journal-title":"Proc ICSLP"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/89.759034"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/ICASSP.1998.675351"},{"key":"ref37","first-page":"757","article-title":"Prob-abilistic and bottle-neck features for LVCSR of meetings","author":"grezl","year":"2007","journal-title":"Proc ICASSP"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/ICASSP.2000.862024"},{"year":"1993","author":"bourlard","journal-title":"Connectionist Speech Recognition A Hybrid Approach","key":"ref35"},{"key":"ref34","first-page":"901","article-title":"SRILM - an extensible language modeling toolkit","author":"stolcke","year":"2002","journal-title":"Proc of ICSLP"},{"key":"ref10","first-page":"436","article-title":"Speech enhancement based on deep denoising auto-encoder","author":"lu","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref40","first-page":"5592","article-title":"Joint acoustic modeling of triphones and trigraphemes by multi-task learning deep neural networks for low-resource speech recognition","author":"chen","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23","author":"xu","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process (TASLP)"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/WASPAA.2013.6701894"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1186\/s13634-016-0306-6"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1016\/j.csl.2012.10.004"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ASRU.2015.7404837"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP.2014.6854745"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/WASPAA.2013.6701861"},{"key":"ref18","first-page":"1","article-title":"Polyphonic sound event detection using multilabel deep neural networks","author":"cakir","year":"2015","journal-title":"Proc IEEE International Joint Conference on Neural Networks (IJCNN)"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/ICASSP.2015.7178031"},{"key":"ref28","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc ASRU"},{"key":"ref4","first-page":"208","article-title":"Enhance-ment of speech corrupted by additive noise","author":"berouti","year":"1979","journal-title":"Proc ICASSP"},{"key":"ref27","first-page":"947","article-title":"Spontaneous speech corpus of Japanese","author":"maekawa","year":"2000","journal-title":"Proc LREC"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1121\/1.1907229"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref29","article-title":"Kaldi+PDNN: building DNN-based ASR systems with Kaldi and PDNN","author":"miao","year":"2014","journal-title":"arXiv 1401 6984"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP.2002.5745591"},{"key":"ref8","first-page":"177","article-title":"A speech enhancement based on kalman filtering","author":"paliwak","year":"1987","journal-title":"Proc ICASSP"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP.2002.5743702"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/MSP.2010.937498"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP.2004.1325982"},{"year":"2013","journal-title":"American Speech Language Hearing Association","article-title":"Hearing and balance","key":"ref1"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1109\/ICASSP.2014.6853591"},{"key":"ref20","article-title":"Scan anything and let your phone do the rest","author":"muller","year":"2011","journal-title":"in MIT technology review technical report"},{"key":"ref45","first-page":"2867","article-title":"Speaker adaptation using the i-vector technique for bottleneck features","author":"cardinal","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref22","article-title":"Ability to listen to two things at once is largely inherited, says twin study","author":"morell","year":"2007","journal-title":"Human Genetics"},{"key":"ref47","first-page":"1898","article-title":"Investigating factor analysis features for deep neural networks in noisy speech recognition","author":"ganapathy","year":"2015","journal-title":"Proc Inter-speech"},{"key":"ref21","first-page":"503","article-title":"Cocktail-party effect with computational auditory scene analysis","volume":"2","author":"okuno","year":"1995","journal-title":"Symbiosis of Human and Artifact (Elsevier)"},{"key":"ref42","first-page":"8619","article-title":"Multilin-gual acoustic models using distributed deep neural networks","author":"heigold","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref24","article-title":"Joint factor analysis of speaker and session variability: Theory and algorithms","author":"kenny","year":"2005","journal-title":"CRIM Tech Rep"},{"key":"ref41","first-page":"312","article-title":"Multitask learning in connectionist speech recognition","author":"lu","year":"2004","journal-title":"10th Australian International Conference on Speech Science & Technology"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1121\/1.415287"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1109\/ASRU.2013.6707705"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/TSA.2004.840940"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref25","first-page":"788","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"dehak","year":"2010","journal-title":"IEEE Trans ASLP"}],"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\/07846242.pdf?arnumber=7846242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,7,25]],"date-time":"2017-07-25T19:30:06Z","timestamp":1501011006000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7846242\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/slt.2016.7846242","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}