{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:08:00Z","timestamp":1764785280162,"version":"3.28.0"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389803","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Mask-Conformer: Augmenting Conformer with Mask-Predict Decoder"],"prefix":"10.1109","author":[{"given":"Yosuke","family":"Higuchi","sequence":"first","affiliation":[{"name":"Google Inc.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Google Inc.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Google Inc.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murali Karthick","family":"Baskar","sequence":"additional","affiliation":[{"name":"Google Inc.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google Inc.,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. ICML","author":"Graves"},{"key":"ref2","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. NeurIPS","author":"Chorowski"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref4","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. NeurIPS","author":"Sutskever"},{"article-title":"Neural machine translation by jointly learning to align and translate","volume-title":"Proc. ICLR","author":"Bahdanau","key":"ref5"},{"article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. ICML Representation Learning Workshop","author":"Graves","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2059"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref10","first-page":"17 627","article-title":"Branchformer: Parallel MLP-attention architectures to capture local and global context for speech recognition and understanding","volume-title":"Proc. ICLR","author":"Peng"},{"key":"ref11","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","author":"Baevski"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-211"},{"article-title":"Transformer transducer: One model unifying streaming and non-streaming speech recognition","volume-title":"arXiv preprint arXiv:2010.03192","author":"Tripathi","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-212"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414495"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639530"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052964"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746580"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688157"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2404"},{"key":"ref32","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional Transformers for language understanding","volume-title":"Proc. NAACL-HLT)","author":"Devlin"},{"key":"ref33","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. NeurIPS","author":"Vaswani"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.402"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3186162"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095186"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2400218"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref40","article-title":"Deliberation networks: Sequence generation beyond one-pass decoding","volume-title":"Proc. NeurIPS","volume":"30","author":"Xia"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746390"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3044547"},{"key":"ref45","first-page":"1403","article-title":"Imputer: Sequence modelling via imputation and dynamic programming","volume-title":"Proc. ICML","author":"Chan"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10062"},{"article-title":"Acoustic-aware non-autoregressive spell correction with mask sample decoding","volume-title":"arXiv preprint arXiv:2210.08665","author":"Fan","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"article-title":"SpeechStew: Simply mix all available speech recognition data to train one large neural network","volume-title":"arXiv preprint arXiv:2104.02133","author":"Chan","key":"ref49"},{"article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","volume-title":"arXiv preprint arXiv:1902.08295","author":"Shen","key":"ref50"},{"article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","volume-title":"arXiv preprint arXiv:1603.04467","author":"Abadi","key":"ref51"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma","key":"ref52"},{"issue":"1","key":"ref53","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume-title":"The journal of machine learning research","volume":"15","author":"Srivastava"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/72.548170"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","volume-title":"arXiv preprint arXiv:2010.10504","author":"Zhang","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-787"},{"article-title":"Intermediate-layer output regularization for attention-based speech recognition with shared decoder","volume-title":"arXiv preprint arXiv:2207.04177","author":"Zhang","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022760"},{"article-title":"Citrinet: Closing the gap between non-autoregressive and autoregressive end-to-end models for automatic speech recognition","volume-title":"arXiv preprint arXiv:2104.01721","author":"Majumdar","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1758"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389803.pdf?arnumber=10389803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T11:33:46Z","timestamp":1706009626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389803","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}