{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T10:30:06Z","timestamp":1760956206122,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095369","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Conditional Conformer: Improving Speaker Modulation For Single And Multi-User Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Tom","family":"O\u2019Malley","sequence":"first","affiliation":[{"name":"Google LLC,U.S.A"}]},{"given":"Shaojin","family":"Ding","sequence":"additional","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":"Rajeev","family":"Rikhye","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A"}]},{"given":"Qiao","family":"Liang","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A"}]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A"}]},{"given":"Ian","family":"McGraw","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref35","first-page":"265","article-title":"Tensorflow: a system for large-scale machine learning","volume":"16","author":"abadi","year":"2016","journal-title":"OSDI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1108\/RR-08-2013-0197"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054328"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682822"},{"article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","year":"2019","author":"shen","key":"ref36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11140"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref33","article-title":"Lib- rispeech: An ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2191"},{"key":"ref32","article-title":"Learning mask scalars for improved robust automatic speech recognition","author":"narayanan","year":"2022","journal-title":"Proc IEEE SLT"},{"key":"ref2","article-title":"Exploring Neural Transducers for End-to-end Speech Recognition","author":"battenberg","year":"2017","journal-title":"Proc of ASRU"},{"key":"ref1","article-title":"A Comparison of Sequence-to-Sequence Models for Speech Recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1009"},{"key":"ref16","article-title":"Streaming multispeaker asr with rnn-t","author":"sklyar","year":"2021","journal-title":"Proc IEEE ICASSP"},{"key":"ref19","first-page":"2728","article-title":"Voice- Filter: Targeted voice separation by speaker-conditioned spectrogram masking","author":"wilson","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref24","article-title":"Multi-user VoiceFilter-Lite via attentive speaker embedding","author":"liang","year":"2021","journal-title":"Proc IEEE ASRU"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-856"},{"key":"ref26","article-title":"Continuous speech separation with con- former","author":"chen","year":"2021","journal-title":"Proc IEEE ICASSP"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-41"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1193"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687942"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00472"},{"article-title":"Searching for activation functions","year":"2017","author":"ramachandran","key":"ref27"},{"article-title":"Understanding and improving transformer from a multi-particle dynamic system point of view","year":"2019","author":"lu","key":"ref29"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","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":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1296"},{"key":"ref6","article-title":"Multi-domain joint semantic frame parsing using bidirectional rnn-lstm","author":"hakkani-tur","year":"2016","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-398"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095369.pdf?arnumber=10095369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T13:56:54Z","timestamp":1699883814000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095369","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}