{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:50:26Z","timestamp":1780318226858,"version":"3.54.1"},"reference-count":5,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10627330","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"123-124","source":"Crossref","is-referenced-by-count":1,"title":["Summary on the Multimodal Information-Based Speech Processing (MISP) 2023 Challenge"],"prefix":"10.1109","author":[{"given":"Hang","family":"Chen","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shilong","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxi","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sabato Marco","family":"Siniscalchi","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingdong","family":"Chen","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Odette","family":"Scharenborg","sequence":"additional","affiliation":[{"name":"Delft University of Technology,The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong-Qiu","family":"Wang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bao-Cai","family":"Yin","sequence":"additional","affiliation":[{"name":"iFlytek,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"iFlytek,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447462"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746683"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSPW62465.2024.10626417","article-title":"Sir-progressive audio-visual tf-gridnet with ASR-aware selector for target speaker extraction in MISP 2023 challenge","volume-title":"Proc. ICASSP 2024","author":"Hou"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSPW62465.2024.10627638","article-title":"An audio-quality-based multi-strategy approach for target speaker extraction in the MISP 2023 challenge","volume-title":"Proc. ICASSP 2024","author":"Han"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSPW62465.2024.10626643","article-title":"The XMUSpeech system for audio-visual target speaker extraction in MISP 2023 challenge","volume-title":"Proc. ICASSP 2024","author":"Luo"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10627330.pdf?arnumber=10627330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T17:18:52Z","timestamp":1723828732000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10627330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":5,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10627330","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}