{"id":"https://openalex.org/W3163346546","doi":"https://doi.org/10.1109/icassp39728.2021.9414244","title":"Multi-Channel Target Speech Extraction with Channel Decorrelation and Target Speaker Adaptation","display_name":"Multi-Channel Target Speech Extraction with Channel Decorrelation and Target Speaker Adaptation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163346546","doi":"https://doi.org/10.1109/icassp39728.2021.9414244","mag":"3163346546"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5090367911","display_name":"Jiangyu Han","orcid":"https://orcid.org/0000-0001-5390-8520"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyu Han","raw_affiliation_strings":["Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102864167","display_name":"Xinyuan Zhou","orcid":"https://orcid.org/0000-0003-2815-8857"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Zhou","raw_affiliation_strings":["Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039983089","display_name":"Yijie Li","orcid":"https://orcid.org/0009-0004-3636-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yijie Li","raw_affiliation_strings":["Unisound AI Technology Co., Ltd., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.853,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.85807056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6094","last_page":"6098"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/decorrelation","display_name":"Decorrelation","score":0.9068537950515747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8110352158546448},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.7412096261978149},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6575504541397095},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5826215744018555},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5072888731956482},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4929351806640625},{"id":"https://openalex.org/keywords/channel-state-information","display_name":"Channel state information","score":0.4742666482925415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33362066745758057},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3334466218948364},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16732999682426453},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16265299916267395},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.05947005748748779}],"concepts":[{"id":"https://openalex.org/C177860922","wikidata":"https://www.wikidata.org/wiki/Q788608","display_name":"Decorrelation","level":2,"score":0.9068537950515747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8110352158546448},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.7412096261978149},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6575504541397095},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5826215744018555},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5072888731956482},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4929351806640625},{"id":"https://openalex.org/C148063708","wikidata":"https://www.wikidata.org/wiki/Q5072511","display_name":"Channel state information","level":3,"score":0.4742666482925415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33362066745758057},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3334466218948364},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16732999682426453},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16265299916267395},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.05947005748748779},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions"}],"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":27,"referenced_works":["https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2892163332","https://openalex.org/W2909607850","https://openalex.org/W2924115626","https://openalex.org/W2939771864","https://openalex.org/W2944972166","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2972802573","https://openalex.org/W2973062255","https://openalex.org/W2973179291","https://openalex.org/W2981976899","https://openalex.org/W3004309045","https://openalex.org/W3015372568","https://openalex.org/W3015636705","https://openalex.org/W3015788098","https://openalex.org/W3015843733","https://openalex.org/W3016257794","https://openalex.org/W3016361963","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W6762182681","https://openalex.org/W6769511080","https://openalex.org/W6769612168"],"related_works":["https://openalex.org/W1604939135","https://openalex.org/W2127058578","https://openalex.org/W2735368845","https://openalex.org/W2089764958","https://openalex.org/W2073586885","https://openalex.org/W2546477360","https://openalex.org/W2359691516","https://openalex.org/W2098040275","https://openalex.org/W2261979314","https://openalex.org/W2221419418"],"abstract_inverted_index":{"The":[0,43,58],"end-to-end":[1,16],"approaches":[2],"for":[3,15,32],"single-channel":[4],"target":[5,18,41,49],"speech":[6,19,50],"extraction":[7,20],"have":[8],"attracted":[9],"widespread":[10],"attention.":[11],"However,":[12],"the":[13,34,40,69,75,81,92,118,126],"studies":[14],"multi-channel":[17,35,76,93],"are":[21,117],"still":[22],"relatively":[23],"limited.":[24],"In":[25],"this":[26,123],"work,":[27],"we":[28],"propose":[29],"two":[30,85],"methods":[31,83,102],"exploiting":[33],"spatial":[36],"information":[37,72],"to":[38,67,73,105,125],"extract":[39,68],"speech.":[42],"first":[44],"one":[45,60],"is":[46,61],"using":[47],"a":[48,54,63],"adaptation":[51],"layer":[52],"in":[53,111],"parallel":[55],"encoder":[56,77],"architecture.":[57],"second":[59],"designing":[62],"channel":[64],"decorrelation":[65],"mechanism":[66],"inter-channel":[70],"differential":[71],"enhance":[74],"representation.":[78],"We":[79],"compare":[80],"proposed":[82,101],"with":[84],"strong":[86],"state-of-the-art":[87],"baselines.":[88],"Experimental":[89],"results":[90,121],"on":[91,122],"reverberant":[94],"WSJ0":[95],"2-mix":[96],"dataset":[97],"demonstrate":[98],"that":[99],"our":[100,129],"achieve":[103],"up":[104],"11.2%":[106],"and":[107,113],"11.5%":[108],"relative":[109],"improvements":[110],"SDR":[112],"SiSDR":[114],"respectively,":[115],"which":[116],"best":[119,127],"reported":[120],"task":[124],"of":[128],"knowledge.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}