{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:33:39Z","timestamp":1776890019720,"version":"3.51.2"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447685","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12026-12030","source":"Crossref","is-referenced-by-count":2,"title":["Transducers with Pronunciation-Aware Embeddings for Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Hainan","family":"Xu","sequence":"first","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhehuai","family":"Chen","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Jia","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The Kaldi speech recognition toolkit","volume-title":"ASRU Workshop","author":"Povey"},{"issue":"175","key":"ref2","first-page":"12","article-title":"The htk book","volume":"3","author":"Young","year":"2002","journal-title":"Cambridge university engineering department"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"ICML"},{"key":"ref5","article-title":"Attention-based models for speech recognition","author":"Chorowski","year":"2015","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","article-title":"Nemo: a toolkit for building AI applications using neural modules","author":"Kuchaiev","year":"2019"},{"key":"ref8","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"Ren","year":"2019","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003968"},{"key":"ref10","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022528"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688053"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383506"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682494"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096062"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687895"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1434"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682441"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref20","article-title":"Aishell-2: Transforming mandarin ASR research into industrial scale","author":"Du","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref22","article-title":"Thchs-30: A free chinese speech corpus","author":"Wang","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5616"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447685.pdf?arnumber=10447685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:57:46Z","timestamp":1722578266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447685","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}