{"id":"https://openalex.org/W4401611032","doi":"https://doi.org/10.1109/icasspw62465.2024.10626643","title":"The Xmuspeech System for Audio-Visual Target Speaker Extraction in Misp 2023 Challenge","display_name":"The Xmuspeech System for Audio-Visual Target Speaker Extraction in Misp 2023 Challenge","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401611032","doi":"https://doi.org/10.1109/icasspw62465.2024.10626643"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626643","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113336137","display_name":"Longjie Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longjie Luo","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,Xiamen,China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455266","display_name":"Tao Li","orcid":"https://orcid.org/0000-0001-9910-2573"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,Xiamen,China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["Xiamen University,School of Informatics,Xiamen,China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,Xiamen,China,361005","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113336137"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65616217,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.968500018119812,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7670572400093079},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6634621620178223},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4492897689342499},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4252907633781433},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.24810856580734253},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06425061821937561}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7670572400093079},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6634621620178223},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4492897689342499},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4252907633781433},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.24810856580734253},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06425061821937561},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626643","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2900212944","https://openalex.org/W4221143458","https://openalex.org/W4392902829"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W1984634519"],"abstract_inverted_index":{"This":[0,52],"paper":[1],"presents":[2],"the":[3,7,31,34,44,55,63,71,75,86,97,103],"XMUSPEECH":[4],"system":[5,84],"for":[6],"Multimodal":[8],"Information":[9],"based":[10],"Speech":[11],"Processing":[12],"(MISP)":[13],"2023":[14],"Challenge.":[15],"The":[16],"primary":[17],"difficulty":[18],"in":[19,23,27],"this":[20],"competition":[21],"lies":[22],"effectively":[24],"suppressing":[25],"noise":[26],"mixture":[28],"while":[29],"maintaining":[30],"integrity":[32],"of":[33,74,92],"target":[35,76],"speaker\u2019s":[36],"speech":[37,49],"signal.":[38],"To":[39],"achieve":[40],"this,":[41],"we":[42],"introduce":[43],"AV-MCCMGAN,":[45],"a":[46,60],"multi-modal":[47],"multichannel":[48],"enhancement":[50],"model.":[51],"model":[53],"employs":[54],"raw":[56],"6-channels":[57],"audio":[58],"as":[59],"supplement":[61],"to":[62,78],"guided":[64],"source":[65],"separation":[66],"(GSS)":[67],"signal":[68],"and":[69,94,99],"utilizes":[70],"visual":[72],"clues":[73],"speaker":[77],"further":[79],"eliminate":[80],"noise.":[81],"Ultimately,":[82],"our":[83],"achieves":[85],"character":[87],"error":[88],"rate":[89],"(CER)":[90],"values":[91],"23.3%":[93],"33.41%":[95],"on":[96],"Dev":[98],"Eval":[100],"set,":[101],"ranking":[102],"third.":[104]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}
