{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:34:04Z","timestamp":1776890044905,"version":"3.51.2"},"reference-count":88,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434782","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["All-in-One ASR: Unifying Encoder-Decoder Models of CTC, Attention, and Transducer in Dual-Mode ASR"],"prefix":"10.1109","author":[{"given":"Takafumi","family":"Moriya","sequence":"first","affiliation":[{"name":"NTT, Inc,Japan"}]},{"given":"Masato","family":"Mimura","sequence":"additional","affiliation":[{"name":"NTT, Inc,Japan"}]},{"given":"Tomohiro","family":"Tanaka","sequence":"additional","affiliation":[{"name":"NTT, Inc,Japan"}]},{"given":"Hiroshi","family":"Sato","sequence":"additional","affiliation":[{"name":"NTT, Inc,Japan"}]},{"given":"Ryo","family":"Masumura","sequence":"additional","affiliation":[{"name":"NTT, Inc,Japan"}]},{"given":"Atsunori","family":"Ogawa","sequence":"additional","affiliation":[{"name":"NTT, Inc,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","article-title":"End-to-End Continuous Speech Recognition Using Attention-based Recurrent NN: First Results","author":"Chorowski","year":"2014","journal-title":"Advances in NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","article-title":"Sequence Transduction with Recurrent Neural Networks","volume-title":"Proc. of ICML","author":"Graves"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-206"},{"key":"ref8","article-title":"Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling","volume-title":"Proc. of ICML","author":"Yu"},{"key":"ref9","first-page":"4835","article-title":"Joint CTC-Attention based End-toEnd Speech Recognition Using Multi-Task Learning","volume-title":"Proc. of ICASSP","author":"Kim"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2263"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2263"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003920"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref17","first-page":"2773","article-title":"Twopass end-to-end speech recognition","volume-title":"Proc. of INTERSPEECH","author":"Sainath"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-437"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746428"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.695"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10022569"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3530324"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-233"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133217"},{"key":"ref27","article-title":"AlignerEncoders: Self-Attention Transformers Can Be Self-Transducers","author":"Stooke","year":"2024","journal-title":"Advances in NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053600"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889391"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3566210"},{"key":"ref32","article-title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint arXiv:2312.00752"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref34","article-title":"Layer Normalization","volume":"abs\/1607.06450","author":"Ba","year":"2016","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413535"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747706"},{"key":"ref37","first-page":"3265432676","article-title":"Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers","volume-title":"Proc. of ICML","author":"Strimel"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097062"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888110"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889802"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2025-1079"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953176"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414716"},{"key":"ref48","article-title":"On Multiplicative Integration with Recurrent Neural Networks","author":"Wu","year":"2016","journal-title":"Advances in NeurIPS"},{"key":"ref49","article-title":"Theory, Analysis, and Best Practices for Sigmoid Self-Attention","volume-title":"Proc. of ICLR","author":"Ramapuram"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095845"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-442"},{"key":"ref52","article-title":"Monotonic Chunkwise Attention","volume-title":"Proc. of ICLR","author":"Chiu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3031480"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/slt48900.2021.9383517"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022818"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10446035"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389635"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9415039"},{"key":"ref59","first-page":"1","article-title":"Fast and Accurate Factorized Neural Transducer for Text Adaption of End-toEnd Speech Recognition Models","volume-title":"Proc. of ICASSP","author":"Zhao"},{"key":"ref60","first-page":"137148","article-title":"On Using Monolingual Corpora in Neural Machine Translation","volume":"45","author":"Gulcehre","year":"2015","journal-title":"Computer Speech & Language"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383515"},{"key":"ref64","first-page":"125","article-title":"TED-LIUM: An Automatic Speech Recognition Dedicated Corpus","volume-title":"Proc. of LREC","author":"Rousseau"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref71","article-title":"Root Mean Square Layer Normalization","author":"Zhang","year":"2019","journal-title":"Advances in NeurIPS"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10340"},{"key":"ref73","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. of ICLR","author":"Kingma"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053040"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688251"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11425"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-7"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889518"},{"key":"ref79","first-page":"6621","article-title":"SpeechT: Transducer for Text to Speech and Beyond","author":"Chen","year":"2021","journal-title":"Advances in NeurIPS"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2383"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1856"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1640"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-999"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref86","article-title":"Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation","volume-title":"Proc. of NeurIPS Workshop on end-to-end learning for speech and audio processing","author":"Berard"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747320"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-349"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434782.pdf?arnumber=11434782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:45Z","timestamp":1775192385000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":88,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434782","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}