{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:26:55Z","timestamp":1775230015362,"version":"3.50.1"},"reference-count":37,"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\/icassp49357.2023.10094660","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Iterative Shallow Fusion of Backward Language Model for End-To-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Atsunori","family":"Ogawa","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takafumi","family":"Moriya","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoyuki","family":"Kamo","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naohiro","family":"Tawara","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383515"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053040"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003790"},{"key":"ref36","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proc ICML"},{"key":"ref31","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref32","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2756440"},{"key":"ref1","author":"xiong","year":"0","journal-title":"Achieving human parity in conversational speech recognition"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1766"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746428"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-11"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-65"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747745"},{"key":"ref22","first-page":"1240","article-title":"Hybrid CTC\/Attention architecture for end-to-end speech recognition","volume":"11","author":"watanabe","year":"2017","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref21","first-page":"3935","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","author":"rousseau","year":"2014","journal-title":"Proc LREC"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref27","article-title":"Back from the future: Bidirectional CTC decoding using future information in speech recognition","author":"jung","year":"0"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861969"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"523","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"949","DOI":"10.21437\/Interspeech.2017-1296","article-title":"Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM","author":"hori","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref4","first-page":"551","article-title":"Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard","author":"t\u00fcske","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref6","author":"gulcehre","year":"0","journal-title":"On using monolingual corpora in neural machine translation"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2062","DOI":"10.21437\/Interspeech.2021-211","article-title":"On the limit of English conversational speech recognition","author":"t\u00fcske","year":"2021","journal-title":"Proc INTERSPEECH"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10094660.pdf?arnumber=10094660","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T22:11:06Z","timestamp":1729375866000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094660\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094660","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}