{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:18:58Z","timestamp":1780773538660,"version":"3.54.1"},"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\/slt61566.2024.10832330","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"193-199","source":"Crossref","is-referenced-by-count":4,"title":["Serialized Speech Information Guidance with Overlapped Encoding Separation for Multi-Speaker Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Hao","family":"Shi","sequence":"first","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta,New York,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2244083"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3407511"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2525"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447667"},{"key":"ref6","article-title":"Enhancing emotion recognition in incomplete data: A novel crossmodal alignment, reconstruction, and refinement framework","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv:2407.09029"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094718"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref10","first-page":"438","article-title":"Spectrograms fusion-based end-to-end robust automatic speech recognition","volume-title":"Proc. APSIPA ASC","author":"Shi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref12","article-title":"Exploration of adapter for noise robust automatic speech recognition","author":"Shi","year":"2024","journal-title":"arXiv preprint arXiv:2402.18275"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-85"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1126"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2519"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2305833"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448116"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446870"},{"key":"ref20","article-title":"How does end-toend speech recognition training impact speech enhancement artifacts?","author":"Iwamoto","year":"2023","journal-title":"arXiv preprint arXiv:2311.11599"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054328"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952154"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-0999"},{"key":"ref25","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","volume-title":"Proc. NIPS","author":"Chorowski"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-564"},{"key":"ref28","article-title":"Speaker mask transformer for multi-talker overlapped speech recognition","author":"Shen","year":"2023","journal-title":"arXiv preprint arXiv:2312.10959"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1236"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446548"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3607865.3613182"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096630"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"ref37","article-title":"LibriMix: An Open-Source Dataset for Generalizable Speech Separation","author":"Cosentino","year":"2020","journal-title":"arXiv preprint arXiv:2005.11262"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10839"},{"key":"ref41","first-page":"3720","article-title":"MultiSpeaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker Chain","volume-title":"Proc. Interspeech","author":"Guo"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1280"},{"key":"ref43","first-page":"1","article-title":"Exploring timefrequency domain target speaker extraction for causal and non-causal processing","volume-title":"Proc. ASRU, 2023","author":"Zhang"},{"key":"ref44","first-page":"1","article-title":"A sidecar separator can convert a singletalker speech recognition system to a multi-talker one","volume-title":"Proc. ICASSP, 2023","author":"Meng"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097139"}],"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\/10832330.pdf?arnumber=10832330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:50:29Z","timestamp":1737100229000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832330","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}