{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:28:44Z","timestamp":1730230124702,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461939","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"4809-4813","source":"Crossref","is-referenced-by-count":8,"title":["Sequence Modeling in Unsupervised Single-Channel Overlapped Speech Recognition"],"prefix":"10.1109","author":[{"given":"Zhehuai","family":"Chen","sequence":"first","affiliation":[]},{"given":"Jasha","family":"Droppo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref11","article-title":"Recognizing multi-talker speech with permutation invariant training","volume":"abs 1704 1985","author":"yu","year":"2017","journal-title":"CoRR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref13","article-title":"Knowledge transfer in permutation invariant training for single-channel multi-talker speech recognition","author":"tan","year":"2018","journal-title":"ICASSP"},{"key":"ref14","first-page":"ii","article-title":"Large vocabulary continuous speech recognition using htk","volume":"2","author":"c woodland","year":"1994","journal-title":"Acoustics Speech and Signal Processing 1994 ICASSP-94 1994 IEEE International Conference on"},{"key":"ref15","article-title":"Recurrent neural aligner: An encoder-decoder neural network model for sequence to sequence mapping","author":"hasim","year":"2017","journal-title":"InterSpeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952120"},{"journal-title":"Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM","year":"2017","author":"hori","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2945397"},{"journal-title":"Achieving human parity in conversational speech recognition","year":"2016","author":"xiong","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.02.006"},{"journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications","year":"2006","author":"wang","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2444659"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015050"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1037\/11496-005"},{"key":"ref7","first-page":"1","article-title":"Progressive joint modeling in unsupervised single-channel overlapped speech recognition","author":"chen","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"journal-title":"Auditory Scene Analysis The Perceptual Organization of Sound","year":"1994","author":"s bregman","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref20","article-title":"Adaptive permutation invariant training with auxiliary information for monaural multi-talker speech recognition","author":"chang","year":"2018","journal-title":"ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref21","article-title":"Listen, attend and spell: A neural network for large vocabulary conversational speech recognition","author":"chan","year":"0","journal-title":"International Conference on Acoustics Speech and Signal Processing (1-CASSP) 2016"},{"key":"ref23","article-title":"On modular training of neural acoustics-to-word model for lvcsr","author":"chen","year":"2018","journal-title":"ICASSP"}],"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\/08461939.pdf?arnumber=8461939","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:04:23Z","timestamp":1598231063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461939\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461939","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}