{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T16:27:40Z","timestamp":1729614460422,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462223","type":"proceedings-article","created":{"date-parts":[[2018,10,9]],"date-time":"2018-10-09T19:40:56Z","timestamp":1539114056000},"page":"5729-5733","source":"Crossref","is-referenced-by-count":3,"title":["Spectral Distortion Model for Training Phase-Sensitive Deep-Neural Networks for Far-Field Speech Recognition"],"prefix":"10.1109","author":[{"given":"Chanwoo","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tara","family":"Sainath","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun","family":"Narayanan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ananya","family":"Misra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajeev","family":"Nongpiur","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michiel","family":"Bacchiani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.07.006"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"2058","DOI":"10.21437\/Interspeech.2010-581","article-title":"Nonlinear enhancement of onset for robust speech recognition","author":"kim","year":"2010","journal-title":"Proc INTERSPEECH 2010"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"2734","DOI":"10.21437\/Interspeech.2014-157","article-title":"Robust speech recognition using temporal masking and thresholding algorithm","author":"kim","year":"2014","journal-title":"Proc INTERSPEECH 2014"},{"key":"ref13","first-page":"286","article-title":"Integrating DNN-based and spatial clustering-based mask estimation for robust MVDR beamforming","author":"nakatani","year":"2017","journal-title":"IEEE Int Conf Acoust Speech Signal Processing"},{"key":"ref14","first-page":"5210","article-title":"Ro-bust MVDR beamforming using time-frequency masks for on-line\/offline ASR in noise","author":"higuchi","year":"2016","journal-title":"IEEE Int Conf Acoust Speech Signal Processing"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"729","DOI":"10.21437\/Interspeech.2010-271","article-title":"Automatic selection of thresholds for signal separation algorithms based on interaural delay","author":"kim","year":"2010","journal-title":"Proc INTERSPEECH 2010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2008.4538697"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"2495","DOI":"10.21437\/Interspeech.2009-372","article-title":"Signal separation for robust speech recognition based on phase difference information obtained in the frequency domain","author":"kim","year":"2009","journal-title":"INTERSPEECH-2009"},{"key":"ref19","first-page":"5072","article-title":"Binaural sound source separation motivated by auditory processing","author":"kim","year":"2011","journal-title":"IEEE Int Conf on Acoustics Speech and Signal Processing"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/2333749"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref27","first-page":"4580","article-title":"Convolutional, long short-term memory, fully connected deep neural networks","author":"sainath","year":"2015","journal-title":"IEEE Int Conf Acoust Speech and Signal Processing"},{"key":"ref3","article-title":"Improving the speed of neural networks on CPU s","author":"vanhoucke","year":"2011","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0_5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1570"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2672401"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-234"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1510"},{"key":"ref2","article-title":"Feature learning in deep neural networks - studies on speech recognition tasks","author":"yu","year":"2013","journal-title":"International Conference on Learning Representations"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2545928"},{"key":"ref1","first-page":"7398","article-title":"An investigation of deep neural networks for noise robust speech recognition","volume":"2013","author":"seltzer","year":"0","journal-title":"Int Conf Acoust Speech and Signal Processing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-28863-5_8"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1109\/ICASSP.1987.1169544","article-title":"Multi-style training for robust isolated-word speech recognition","volume":"12","author":"lippmann","year":"1987","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.1610463"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"1468","DOI":"10.21437\/Interspeech.2015-350","article-title":"Fast and Accurate Recurrent Neural Network Acoustic Models for Speech Recognition","author":"sak","year":"2015","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref23","first-page":"1","article-title":"Learning the Speech Front-end With Raw Waveform CLDNNs","author":"sainath","year":"2015","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1459"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462223.pdf?arnumber=8462223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,3]],"date-time":"2022-09-03T17:53:40Z","timestamp":1662227620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462223","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}