{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:39:31Z","timestamp":1783183171960,"version":"3.54.6"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832263","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"578-585","source":"Crossref","is-referenced-by-count":2,"title":["Optimizing Dysarthria Wake-Up Word Spotting: an End-to-End Approach For SLT 2024 LRDWWS Challenge"],"prefix":"10.1109","author":[{"given":"Shuiyun","family":"Liu","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxiang","family":"Kong","sequence":"additional","affiliation":[{"name":"Xiaomi Inc.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengcheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiji","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Xiaomi Inc.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"Xiaomi Inc.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujun","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiaomi Inc.,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053313"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096075"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448040"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1242"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1921"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s40860-019-00085-y"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746855"},{"key":"ref8","first-page":"1","article-title":"Improved end-to-end dysarthric speech recognition via meta-learning based model reinitialization","volume-title":"Proc. ISCSLP. 2021","author":"Wang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097275"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3091805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5220\/0009163000002513"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1206"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1384"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1427"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414644"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-149"},{"key":"ref17","article-title":"Accurate synthesis of dysarthric speech for ASR data augmentation","volume-title":"CoRR","volume":"abs\/2308.08438","author":"Soleymanpour"},{"key":"ref18","article-title":"Synthesizing dysarthric speech using multi-talker TTS for dysarthric speech recognition","volume-title":"CoRR","volume":"abs\/2201.11571","author":"Soleymanpour"},{"key":"ref19","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NIPS","author":"Baevski"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10674"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-879"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-9996"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref28","article-title":"MUSAN: A music, speech, and noise corpus","volume-title":"CoRR","volume":"abs\/1510.08484","author":"Snyder"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICEPE50861.2021.9404373"},{"key":"ref30","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML. 2021, Proceedings of Machine Learning Research","author":"Kim"},{"key":"ref31","article-title":"Libriheavy: a 50, 000 hours ASR corpus with punctuation casing and context","volume-title":"CoRR","volume":"abs\/2309.08105","author":"Kang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref35","article-title":"AISHELL-2: transforming mandarin ASR research into industrial scale","volume-title":"CoRR","volume":"abs\/1808.10583","author":"Du"},{"key":"ref36","first-page":"10254","article-title":"ACAV 100M: automatic curation of large-scale datasets for audio-visual video representation learning","volume-title":"Proc. ICCV. 2021","author":"Lee"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096736"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095459"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832263.pdf?arnumber=10832263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:19:03Z","timestamp":1737101943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832263","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}