{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T09:33:46Z","timestamp":1774690426374,"version":"3.50.1"},"reference-count":45,"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\/asru51503.2021.9688173","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"312-319","source":"Crossref","is-referenced-by-count":8,"title":["Cross-Attention Conformer for Context Modeling in Speech Enhancement for ASR"],"prefix":"10.1109","author":[{"given":"Arun","family":"Narayanan","sequence":"first","affiliation":[{"name":"Google LLC,U.S.A."}]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}]},{"given":"Tom","family":"O'Malley","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}]},{"given":"Quan","family":"Wang","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854051"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","article-title":"A streaming on-device end-to-end model sur-passing server-side conventional model quality and la-tency","author":"sainath","year":"0","journal-title":"Proc ICASSP"},{"key":"ref32","article-title":"Textual echo cancellation","author":"ding","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref31","article-title":"Paral-lel rescoring with transformer for streaming on-device speech recognition","author":"li","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref30","article-title":"Listen, at-tend and spell: A neural network for large vocabulary conversational speech recognition","author":"chan","year":"0","journal-title":"Proc ICASSP"},{"key":"ref37","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref34","article-title":"FiLM: Visual reasoning with a general conditioning layer","author":"de vries","year":"0","journal-title":"Proceedings of the AAAI Confer-ence on Artificial Intelligence"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2191"},{"key":"ref40","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume":"16","author":"abadi","year":"0","journal-title":"OSDI"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413423"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref16","article-title":"Ideal ratio mask es-timation using deep neural networks for robust speech recognition","author":"narayanan","year":"0","journal-title":"Proc ICASSP"},{"key":"ref17","article-title":"Tune-in: Training under negative environments with interference for attention networks simulating cocktail party effect","author":"wang","year":"0","journal-title":"Proc AAAI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1563"},{"key":"ref19","article-title":"An investigation of deep neural networks for noise robust speech recog-nition","author":"seltzer","year":"0","journal-title":"Proc ICASSP"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"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":"ref29","article-title":"Sequence Transduction with Recurrent Neural Networks","author":"graves","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-398"},{"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":"ref2","article-title":"Exploring Neural Transducers for End-to-end Speech Recog-nition","author":"battenberg","year":"0","journal-title":"Proc ASRU"},{"key":"ref9","article-title":"SpecAugment: A simple data augmentation method for automatic speech recog-nition","author":"park","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","article-title":"A Comparison of Sequence-to-Sequence Models for Speech Recognition","author":"prabhavalkar","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref20","article-title":"Hot-word cleaner: dual-microphone adaptive noise cancellation with deferred filter coefficients for robust keyword spotting","author":"huang","year":"0","journal-title":"Proc ICASSP"},{"key":"ref45","article-title":"End-to-end multi-person audio\/visual automatic speech recog-nition","author":"braga","year":"0","journal-title":"Proc ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1193"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref24","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"ADVANCES IN NEURAL IN-FORMATION PROCESSING SYSTEMS"},{"key":"ref41","article-title":"Lingvo: A Modular and Scalable Framework for Sequence-to-Sequence Modeling","author":"shen","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref23","first-page":"92","article-title":"Improving robustness of deep neural network acoustic models via speech sepa-ration and joint adaptive training","volume":"23","author":"narayanan","year":"2015","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref44","article-title":"Multi-user voicefilter-lite via attentive speaker embed-ding","author":"rikhye","year":"0","journal-title":"Under review IEEE ASRU"},{"key":"ref26","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"yeh","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Con-former: Convolution-augmented transformer for speech recognition","author":"gulati","year":"0","journal-title":"Proc INTERSPEECH"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"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\/09688173.pdf?arnumber=9688173","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:02Z","timestamp":1652733722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688173\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688173","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}