{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:12Z","timestamp":1775230152594,"version":"3.50.1"},"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\/icassp48485.2024.10448264","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"10536-10540","source":"Crossref","is-referenced-by-count":10,"title":["PromptASR for Contextualized ASR with Controllable Style"],"prefix":"10.1109","author":[{"given":"Xiaoyu","family":"Yang","sequence":"first","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Wei","family":"Kang","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Zengwei","family":"Yao","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Yifan","family":"Yang","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Liyong","family":"Guo","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Fangjun","family":"Kuang","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Long","family":"Lin","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]},{"given":"Daniel","family":"Povey","sequence":"additional","affiliation":[{"name":"Xiaomi Corp.,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1991.150436"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688232"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1566"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687915"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-767"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095204"},{"key":"ref8","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688079"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389732"},{"key":"ref13","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451760"},{"key":"ref16","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref19","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","author":"Yao","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10340"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"Snyder","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"}],"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\/10448264.pdf?arnumber=10448264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:51:20Z","timestamp":1722660680000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448264","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}