{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:40:21Z","timestamp":1737103221111,"version":"3.33.0"},"reference-count":30,"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\/slt61566.2024.10832166","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"56-63","source":"Crossref","is-referenced-by-count":0,"title":["Spatialemb: Extract and Encode Spatial Information for 1-Stage Multi-Channel Multi-Speaker ASR on Arbitrary Microphone Arrays"],"prefix":"10.1109","author":[{"given":"Yiwen","family":"Shao","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,WA,USA"}]},{"given":"Sanjeev","family":"Khudanpur","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Bellevue,WA,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1167"},{"article-title":"Gpuaccelerated guided source separation for meeting transcription","volume-title":"arXiv preprint arXiv:2212.05271","author":"Raj","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3229261"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-570"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3078883"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413594"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023199"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746678"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022715"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639593"},{"key":"ref12","article-title":"Rirsf: Room impulse response based spatial feature for multi-channel multi-talker asr","author":"Shao","year":"2023","journal-title":"arXiv preprint arXiv:2311.00146"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2274"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054177"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746876"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448072"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"article-title":"Nextformer: A convnext augmented conformer for end-to-end speech recognition","volume-title":"arXiv preprint arXiv:2206.14747","author":"Jiang","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1768"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760429"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-430"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747346"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414123"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-655"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10340"},{"key":"ref27","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","author":"Yao","year":"2023","journal-title":"arXiv preprint arXiv:2310.11230"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746465"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746246"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747381"}],"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\/10832166.pdf?arnumber=10832166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:08:10Z","timestamp":1737101290000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832166","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}