{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T23:45:08Z","timestamp":1772235908109,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461883","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"571-5718","source":"Crossref","is-referenced-by-count":14,"title":["Knowledge Transfer in Permutation Invariant Training for Single-Channel Multi-Talker Speech Recognition"],"prefix":"10.1109","author":[{"given":"Tian","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","first-page":"8614","article-title":"Deep Convolutional Neural Networks for LVCSR","author":"tara","year":"2013","journal-title":"ICASSP IEEE"},{"key":"ref31","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref30","article-title":"An Introduction to Computational Networks and the Computational Network Toolkit","author":"yu","year":"2014","journal-title":"Microsoft Technical Report MSR-TR-2014–112"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref13","first-page":"241","article-title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-Talker Speech Separation","author":"yu","year":"2017","journal-title":"ICA SSP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"2456","DOI":"10.21437\/Interspeech.2017-305","article-title":"Recognizing Multi-talker Speech with Permutation Invariant Training","author":"yu","year":"2017","journal-title":"InterSpeech"},{"key":"ref16","article-title":"Single-Channel Multi-talker Speech Recognition with Permutation Invariant Training","volume":"abs 1707 6527","author":"qian","year":"2017","journal-title":"CoRR"},{"key":"ref17","article-title":"Adaptive Permutation Invariant Training with Auxiliary Information for Monaural Multi-Talker Speech Recognition","author":"chang","year":"2018","journal-title":"ICASSP"},{"key":"ref18","article-title":"Sequence Modeling in Unsupervised Single-channel Overlapped Speech Recognition","author":"chen","year":"2018","journal-title":"ICASSP"},{"key":"ref19","first-page":"2654","article-title":"Do Deep Nets Really Need to be Deep?","author":"ba","year":"2014","journal-title":"NIPS"},{"key":"ref28","article-title":"The AMI Meeting Corpus","volume":"88","author":"mccowan","year":"2005","journal-title":"Proc Int Conf Methods Tech Behav Res"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups","volume":"29","author":"geoffrey","year":"2012","journal-title":"IEEE Signal Processing Magazine"},{"key":"ref6","article-title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"ICML"},{"key":"ref29","article-title":"CSR-I (WSJO) Complete LDC93S6A","author":"john","year":"1993","journal-title":"Philadelphia Linguistic Data Consortium"},{"key":"ref5","first-page":"3214","article-title":"A Time Delay Neural Network Architecture for Efficient Modeling of Long Temporal Contexts","author":"peddinti","year":"2015","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953159"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-251"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","article-title":"Context-dependent Pre-trained Deep Neural Networks for Large-vocabulary Speech Recognition","volume":"20","author":"george","year":"2012","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process (TASLP)"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1670","DOI":"10.1109\/TASLP.2015.2444659","article-title":"Deep Neural Networks for Single-Channel Multi-talker Speech Recognition","volume":"23","author":"chao","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process (TASLP)"},{"key":"ref1","author":"yu","year":"2014","journal-title":"Automatic Speech Recognition A Deep Learning Approach Signals and Communication Technology"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2014-432","article-title":"Learning Small-Size DNN with Output-Distribution-Based Criteria","author":"li","year":"2014","journal-title":"InterSpeech"},{"key":"ref22","article-title":"Distilling the Knowledge in a Neural Network","volume":"abs 1503 2531","author":"hinton","year":"2015","journal-title":"CoRR"},{"key":"ref21","article-title":"Transferring Knowledge from a RNN to a DNN","author":"chan","year":"2015","journal-title":"InterSpeech"},{"key":"ref24","first-page":"5275","article-title":"Student-Teacher Network Learning With Enhanced Features","author":"watanabe","year":"2017","journal-title":"InterSpeech"},{"key":"ref23","first-page":"4820","article-title":"Knowledge Distillation for Small-Footprint Highway Networks","author":"lu","year":"2017","journal-title":"ICASSP IEEE"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2765834"},{"key":"ref25","first-page":"2386","article-title":"Large-Scale Domain Adaptation via Teacher-Student Learning","author":"jinyu","year":"2017","journal-title":"InterSpeech"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"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\/08461883.pdf?arnumber=8461883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T17:57:22Z","timestamp":1751997442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461883\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461883","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}