{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:46:52Z","timestamp":1764398812674,"version":"3.46.0"},"reference-count":28,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249305","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"980-985","source":"Crossref","is-referenced-by-count":0,"title":["Real-time VAD-less Speech Recognition by Fine-tuning SSL Model with Data Containing Tagged Non-speech Segments"],"prefix":"10.1109","author":[{"given":"Jotaro","family":"Emoto","sequence":"first","affiliation":[{"name":"Tokushima University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryota","family":"Nishimura","sequence":"additional","affiliation":[{"name":"Toyohashi University of Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kengo","family":"Ohta","sequence":"additional","affiliation":[{"name":"National Institute of Technology Anan College,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norihide","family":"Kitaoka","sequence":"additional","affiliation":[{"name":"Toyohashi University of Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","year":"2020","author":"Baevski","key":"ref1"},{"journal-title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","year":"2021","author":"Hsu","key":"ref2"},{"key":"ref3","first-page":"8440","article-title":"Unsupervised Cross-lingual Representation Learning at Scale","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Conneau"},{"journal-title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","year":"2021","author":"Babu","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-631"},{"journal-title":"Injecting Text and Cross-lingual Supervision in Few-shot Learning from Self-Supervised Models","year":"2021","author":"Wiesner","key":"ref6"},{"journal-title":"Wav2Vec-Aug: Improved self-supervised training with limited data","year":"2022","author":"Sriram","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9747379"},{"journal-title":"End-to-End Automatic Speech Recognition Integrated With CTCBased Voice Activity Detection","year":"2020","author":"Yoshimura","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref11","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"International conference on machine learning","author":"Graves","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-260"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"journal-title":"ReazonSpeech: A Free and Massive Corpus for Japanese ASR","year":"2016","author":"Yin","key":"ref14"},{"issue":"3","key":"ref15","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","article-title":"Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems","volume":"12","author":"Andrew","year":"1993","journal-title":"Speech Communication"},{"journal-title":"Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates","year":"2018","author":"Kudo","key":"ref16"},{"journal-title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","year":"2018","author":"Kudo","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1250\/ast.20.199"},{"journal-title":"Common Voice: A Massively-Multilingual Speech Corpus","year":"2020","author":"Ardila","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-560"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"journal-title":"Robust Speech Recognition via Large-Scale Weak Supervision","year":"2022","author":"Radford","key":"ref22"},{"key":"ref23","first-page":"17","article-title":"Turning whisper into real-time transcription system","volume-title":"Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations","author":"Mach\u00e1\u010dek"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1814"},{"journal-title":"Conformer: Convolutionaugmented Transformer for Speech Recognition","year":"2020","author":"Gulati","key":"ref25"},{"journal-title":"Fast conformer with linearly scalable attention for efficient speech recognition","year":"2023","author":"Rekesh","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413692"},{"journal-title":"Bridging the gap between streaming and non-streaming ASR systems bydistilling ensembles of CTC and RNN-T models","year":"2021","author":"Doutre","key":"ref28"}],"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\/11249305.pdf?arnumber=11249305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:45:33Z","timestamp":1764398733000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249305\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249305","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}