{"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":1776890019378,"version":"3.51.2"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434717","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Masked Self-distilled Transducer-based Keyword Spotting with Semi-autoregressive Decoding"],"prefix":"10.1109","author":[{"given":"Yu","family":"Xi","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"}]},{"given":"Xiaoyu","family":"Gu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"}]},{"given":"Haoyu","family":"Li","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba,China"}]},{"given":"Jun","family":"Song","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba,China"}]},{"given":"Bo","family":"Zheng","sequence":"additional","affiliation":[{"name":"Taobao & Tmall Group of Alibaba,China"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1485"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-480"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746647"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-789"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/TASLPRO.2025.3587459","article-title":"MFA-KWS: Effective keyword spotting with multi-head frame-asynchronous decoding","author":"Xi","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref8","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","volume":"abs\/1910.12977","author":"Yeh","year":"2019","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref13","article-title":"VALL-T: decoder-only generative transducer for robust and decoding-controllable text-to-speech","volume":"abs\/2401.14321","author":"Du","year":"2024","journal-title":"CoRR"},{"key":"ref14","first-page":"474","article-title":"Streaming small-footprint keyword spotting using sequence-tosequence models","volume-title":"Proc. IEEE ASRU","author":"He"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053191"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414339"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413588"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10258"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446909"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389755"},{"key":"ref21","article-title":"Three-in-one: Fast and accurate transducer for hybrid-autoregressive speech recognition","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Xu"},{"key":"ref22","article-title":"Nemo: a toolkit for building ai applications using neural modules","volume-title":"NeurIPS Workshop on Systems for ML","author":"Kuchaiev"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10340"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054419"},{"issue":"56","key":"ref25","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","article-title":"AISHELL-2: transforming mandarin ASR research into industrial scale","author":"Du","year":"2018","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2019.2936282"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461404"},{"key":"ref33","article-title":"Learning pronunciation from a foreign language in speech synthesis networks","volume-title":"CoRR","volume":"abs\/1811.09364","author":"Lee","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref35","article-title":"Decoupled weight decay regularization","volume-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019","author":"Loshchilov"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434717.pdf?arnumber=11434717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:45Z","timestamp":1775192325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434717","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}