{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T10:10:55Z","timestamp":1767262255841,"version":"3.33.0"},"reference-count":45,"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\/slt61566.2024.10832212","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"1068-1075","source":"Crossref","is-referenced-by-count":1,"title":["CTC-GMM: CTC Guided Modality Matching For Fast and Accurate Streaming Speech Translation"],"prefix":"10.1109","author":[{"given":"Rui","family":"Zhao","sequence":"first","affiliation":[{"name":"Microsoft,USA"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}]},{"given":"Ruchao","family":"Fan","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}]},{"given":"Matt","family":"Post","sequence":"additional","affiliation":[{"name":"Microsoft,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.661"},{"article-title":"Listen and translate: A proof of concept for end-to-end speech-to-text translation","volume-title":"NIPS Workshop on End-to-end Learning for Speech and Audio Processing","author":"Berard","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-503"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/iberspeech.2018-13"},{"key":"ref5","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref7","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv preprint arXiv:1409.0473"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414897"},{"article-title":"Monotonic chunkwise attention","volume-title":"International Conference on Learning Representations","author":"Chiu","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1126"},{"article-title":"Monotonic multihead attention","volume-title":"Proceedings of International Conference on Learning Representations","author":"Ma","key":"ref11"},{"key":"ref12","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint arXiv:2312.05187"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10953"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389799"},{"year":"2024","key":"ref20","article-title":"Announcing video translation & speech translation API enhancements"},{"year":"2024","key":"ref21","article-title":"Introducing Copilot+ PCs"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.iwslt-1.8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref25","article-title":"FLEURS: Few-shot learning evaluation of universal representations of speech","author":"Conneau","year":"2022","journal-title":"arXiv preprint arXiv:2205.12446"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2027"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.57"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3263789"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3379877"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-592"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10937"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688101"},{"key":"ref34","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref35","article-title":"Soundstorm: Efficient parallel audio generation","author":"Borsos","year":"2023","journal-title":"arXiv preprint arXiv:2305.09636"},{"article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. ICML","author":"Ju","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687874"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-599"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446985"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424210"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413535"},{"key":"ref44","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics","author":"Papineni"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.213"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","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\/10832212.pdf?arnumber=10832212","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:50:03Z","timestamp":1737100203000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832212\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832212","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}