{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:11:39Z","timestamp":1764400299777,"version":"3.46.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20315"],"award-info":[{"award-number":["U23A20315"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4500600"],"award-info":[{"award-number":["2022YFB4500600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249276","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"519-524","source":"Crossref","is-referenced-by-count":0,"title":["Language Adaptation Wake Word Spotting via Latent Space from Pre-Trained Speech Models"],"prefix":"10.1109","author":[{"given":"Shifu","family":"Xiong","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengshun","family":"Zhou","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,Anhui,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Shen","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,Anhui,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shi","family":"Cheng","sequence":"additional","affiliation":[{"name":"iFlytek Research,Hefei,Anhui,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Genshun","family":"Wan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kewei","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lirong","family":"Dai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-107"},{"key":"ref2","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"volume-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","year":"2020","author":"Zhang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref7","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095929"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447258"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-633"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1184"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096384"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1210"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096736"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095428"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747295"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10269"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094747"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746360"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095444"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682534"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-2362"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10558"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icasspw59220.2023.10193371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095383"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"article-title":"The npu system for the 2020 personalized voice trigger challenge","volume-title":"2021","author":"Hou","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/asru57964.2023.10389676"},{"journal-title":"Owsm v3.1: Better and faster open whisper-style speech models based on e-branchformer","year":"2024","author":"Peng","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094623"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846306"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054039"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683557"},{"volume-title":"Distilwhisper: Robust knowledge distillation via large-scale pseudo labelling","year":"2023","author":"Gandhi","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095400"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249276.pdf?arnumber=11249276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:09:14Z","timestamp":1764400154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249276","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}