{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:56Z","timestamp":1775230136077,"version":"3.50.1"},"reference-count":30,"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\/icassp48485.2024.10447652","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10641-10645","source":"Crossref","is-referenced-by-count":9,"title":["Phoneme-Aware Encoding for Prefix-Tree-Based Contextual ASR"],"prefix":"10.1109","author":[{"given":"Hayato","family":"Futami","sequence":"first","affiliation":[{"name":"Sony Group Corporation"}]},{"given":"Emiru","family":"Tsunoo","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}]},{"given":"Yosuke","family":"Kashiwagi","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}]},{"given":"Hiroaki","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Sony Group Corporation"}]},{"given":"Siddhant","family":"Arora","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3328283"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413962"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746126"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1566"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383560"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687915"},{"key":"ref10","article-title":"Graph neural networks for contextual ASR with the tree-constrained pointer generator","author":"Sun","year":"2023","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1440"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"ref13","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1434"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096062"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846248"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11066"},{"key":"ref19","article-title":"Applying many-to-many alignments and hidden markov models to letter-to-phoneme conversion","volume-title":"NAACL","author":"Jiampojamarn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.01.002"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324915000315"},{"key":"ref22","article-title":"Attention-based models for speech recognition","volume-title":"NIPS","author":"Chorowski"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref24","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"ICLR","author":"Kipf"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP40776.2020.9053205","article-title":"Specaugment on large scale datasets","volume-title":"ICASSP","author":"Park"},{"key":"ref30","article-title":"Corpus of Spontaneous Japanese : its design and evaluation","volume-title":"SSPR","author":"Maekawa"}],"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\/10447652.pdf?arnumber=10447652","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:54:56Z","timestamp":1722578096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447652\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447652","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}