{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T08:27:10Z","timestamp":1765268830446,"version":"3.28.0"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9687942","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"304-311","source":"Crossref","is-referenced-by-count":16,"title":["A Conformer-Based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation"],"prefix":"10.1109","author":[{"given":"Tom","family":"O'Malley","sequence":"first","affiliation":[{"name":"Google LLC,U.S.A"}]},{"given":"Arun","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A"}]},{"given":"Quan","family":"Wang","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A"}]},{"given":"Alex","family":"Park","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A"}]},{"given":"James","family":"Walker","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A"}]},{"given":"Nathan","family":"Howard","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682682"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"ref33","article-title":"Wavesplit: End-to-end speech separation by speaker clustering","author":"zeghidour","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1205"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413585"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1484"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2730"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref29","article-title":"Speaker-aware neural network based beamformer for speaker extraction in speech mixtures","author":"zmolikova","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref2","article-title":"Exploring Neural Transducers for End-to-end Speech Recognition","author":"battenberg","year":"0","journal-title":"Proc of ASRU"},{"key":"ref1","article-title":"A Comparison of Sequence-to-Sequence Models for Speech Recognition","author":"prabhavalkar","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2908"},{"key":"ref22","article-title":"Textual echo cancellation","author":"ding","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3330393.3330399"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1987.1169544"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref25","article-title":"End-to-end multi-talker over-lapping speech recognition","author":"tripathi","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref50","first-page":"265","article-title":"Tensorflow: a system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"OSDI"},{"key":"ref51","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"journal-title":"Lingvo a Modular and Scalable Framework for Sequence-to-Sequence Modeling","year":"2019","author":"shen","key":"ref52"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2191"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref14","volume":"40","author":"h\u00e4usler","year":"2005","journal-title":"Acoustic Echo and Noise Control A Practical Approach"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04437-7"},{"key":"ref16","first-page":"485","article-title":"An auditory scene analysis approach to monaural speech segregation","author":"hu","year":"2006","journal-title":"Topics in Acoustic Echo and Noise Control"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-22574-1"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1016\/B978-0-12-396501-1.00030-3","article-title":"Acoustic echo control","volume":"4","author":"enzner","year":"2014","journal-title":"Academic Press Library in Signal Processing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1484"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref3","article-title":"Advances in Joint CTC-Attention Based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM","author":"hori","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-402"},{"key":"ref5","article-title":"On multi-domain training and adaptation of end-to-end rnn acoustic models for distant speech recognition","author":"mirsamadi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref8","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home","author":"kim","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref49","article-title":"Lib-rispeech: An ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref46","article-title":"FiLM: Visual reasoning with a general conditioning layer","author":"perez","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref45","article-title":"Version control of speaker recognition systems","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688173"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"key":"ref44","article-title":"More ways to fine tune Google Assistant for you","author":"jensen","year":"2020","journal-title":"Google Assistant"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-641"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09687942.pdf?arnumber=9687942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:41Z","timestamp":1652733701000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687942","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}