{"id":"https://openalex.org/W4225592424","doi":"https://doi.org/10.1109/asru51503.2021.9687903","title":"Attention-Based Scaling Adaptation for Target Speech Extraction","display_name":"Attention-Based Scaling Adaptation for Target Speech Extraction","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4225592424","doi":"https://doi.org/10.1109/asru51503.2021.9687903"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687903","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"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":true,"raw_author_name":"Jiangyu Han","raw_affiliation_strings":["Shanghai Normal University,Shanghai,China","Shanghai Normal University, Shanghai, China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,Shanghai,China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035226758","display_name":"Wei Rao","orcid":"https://orcid.org/0000-0002-7237-0874"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Rao","raw_affiliation_strings":["Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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","Shanghai Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,Shanghai,China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110832899","display_name":"Jiaen Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaen Liang","raw_affiliation_strings":["Unisound AI Technology Co., Ltd.,Beijing,China","Unisound AI Technology Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Unisound AI Technology Co., Ltd.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090367911"],"corresponding_institution_ids":["https://openalex.org/I21945476","https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":1.8924,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.92343855,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"658","last_page":"662"},"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":0.9990000128746033,"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.8191812038421631},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7460222244262695},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6385940909385681},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5890966653823853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5814980268478394},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5467402935028076},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5392983555793762},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5178290009498596},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4839642345905304},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.45289745926856995},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44790101051330566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39622971415519714},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3554040491580963},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07823607325553894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06810897588729858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191812038421631},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7460222244262695},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6385940909385681},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5890966653823853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5814980268478394},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5467402935028076},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5392983555793762},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5178290009498596},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4839642345905304},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.45289745926856995},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44790101051330566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39622971415519714},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3554040491580963},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07823607325553894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06810897588729858},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687903","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G5386056758","display_name":null,"funder_award_id":"62071302,61701306","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":29,"referenced_works":["https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2891833136","https://openalex.org/W2892163332","https://openalex.org/W2909607850","https://openalex.org/W2938646939","https://openalex.org/W2939771864","https://openalex.org/W2944972166","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2981976899","https://openalex.org/W3004940340","https://openalex.org/W3015306128","https://openalex.org/W3015636705","https://openalex.org/W3015654783","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/W3197629192","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6762182681","https://openalex.org/W6769511080","https://openalex.org/W6769827846"],"related_works":["https://openalex.org/W1496222301","https://openalex.org/W3207760230","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297","https://openalex.org/W4280645561"],"abstract_inverted_index":{"The":[0],"target":[1,26,32,59,79,107],"speech":[2,108],"extraction":[3,109],"has":[4],"attracted":[5],"widespread":[6],"attention":[7,39],"in":[8,46,82,122],"recent":[9],"years.":[10],"In":[11],"this":[12],"work,":[13],"we":[14,112],"focus":[15],"on":[16,89],"investigating":[17],"the":[18,25,30,54,58,78,90,98,103,106,116,120],"dynamic":[19],"interaction":[20],"between":[21],"different":[22],"mixtures":[23,136],"and":[24],"speaker":[27,33,80],"to":[28,51],"exploit":[29,77],"discriminative":[31],"clues.":[34],"We":[35],"propose":[36],"a":[37,47,64,83,123],"special":[38],"mechanism":[40],"without":[41],"introducing":[42,63],"any":[43],"additional":[44],"parameters":[45],"scaling":[48,73],"adaptation":[49,74],"layer":[50],"better":[52],"adapt":[53],"network":[55,118],"towards":[56],"extracting":[57],"speech.":[60],"Furthermore,":[61,111],"by":[62],"mixture":[65],"embedding":[66],"matrix":[67],"pooling":[68],"method,":[69],"our":[70],"proposed":[71,99],"attention-based":[72],"(ASA)":[75],"can":[76,101,126],"clues":[81],"more":[84],"efficient":[85],"way.":[86],"Experimental":[87],"results":[88],"spatialized":[91],"reverberant":[92],"WSJ0":[93],"2-mix":[94],"dataset":[95],"demonstrate":[96],"that":[97,114,132],"method":[100],"improve":[102],"performance":[104,129],"of":[105],"effectively.":[110],"find":[113],"under":[115],"same":[117],"configurations,":[119],"ASA":[121],"single-channel":[124],"condition":[125],"achieve":[127],"competitive":[128],"gains":[130],"as":[131],"achieved":[133],"from":[134],"two-channel":[135],"with":[137],"inter-microphone":[138],"phase":[139],"difference":[140],"(IPD)":[141],"features.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}