{"id":"https://openalex.org/W4392902441","doi":"https://doi.org/10.1109/icassp48485.2024.10446845","title":"Implicit Enhancement of Target Speaker in Speaker-Adaptive ASR through Efficient Joint Optimization","display_name":"Implicit Enhancement of Target Speaker in Speaker-Adaptive ASR through Efficient Joint Optimization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902441","doi":"https://doi.org/10.1109/icassp48485.2024.10446845"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101925641","display_name":"Minghui Wu","orcid":"https://orcid.org/0000-0001-8179-7119"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghui Wu","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101089791","display_name":"Haitao Tang","orcid":"https://orcid.org/0000-0002-1507-7890"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haitao Tang","raw_affiliation_strings":["iFLYTEK Research,China","iFLYTEK Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319147","display_name":"Jiahuan Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahuan Fan","raw_affiliation_strings":["iFLYTEK Research,China","iFLYTEK Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033777521","display_name":"Ruoyu Wang","orcid":"https://orcid.org/0000-0002-3644-1284"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoyu Wang","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442517","display_name":"Hang Chen","orcid":"https://orcid.org/0009-0008-7585-033X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053344541","display_name":"Yanyong Zhang","orcid":"https://orcid.org/0000-0001-6520-255X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyong Zhang","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,China","University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103235094","display_name":"Hengshun Zhou","orcid":"https://orcid.org/0000-0001-7878-6531"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hengshun Zhou","raw_affiliation_strings":["iFLYTEK Research,China","iFLYTEK Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037734167","display_name":"Lei Sun","orcid":"https://orcid.org/0000-0001-9046-6485"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Sun","raw_affiliation_strings":["iFLYTEK Research,China","iFLYTEK Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025259327","display_name":"Xin Fang","orcid":"https://orcid.org/0000-0002-6846-7147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Fang","raw_affiliation_strings":["iFLYTEK Research,China","iFLYTEK Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101258932","display_name":"Tian Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Gao","raw_affiliation_strings":["iFLYTEK Research,China","iFLYTEK Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011133553","display_name":"Genshun Wan","orcid":"https://orcid.org/0000-0002-5813-9430"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Genshun Wan","raw_affiliation_strings":["iFLYTEK Research,China","iFLYTEK Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076812698","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0001-9003-2054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFLYTEK Research,China","iFLYTEK Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100730084","display_name":"Jianqing Gao","orcid":"https://orcid.org/0000-0003-1052-7060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianqing Gao","raw_affiliation_strings":["iFLYTEK Research,China","iFLYTEK Research, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK Research, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10051","last_page":"10055"},"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":0.9998999834060669,"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":0.9994000196456909,"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":0.8250982761383057},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.753488302230835},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.71012282371521},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6675761938095093},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5554357171058655},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5472840070724487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48752161860466003},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41414085030555725},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34230032563209534},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06520706415176392}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250982761383057},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.753488302230835},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.71012282371521},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6675761938095093},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5554357171058655},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5472840070724487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48752161860466003},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41414085030555725},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34230032563209534},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06520706415176392},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/7","display_name":"Affordable and clean energy","score":0.4399999976158142}],"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":23,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989314204","https://openalex.org/W2219249508","https://openalex.org/W2327501763","https://openalex.org/W2884797218","https://openalex.org/W2900212944","https://openalex.org/W2963839617","https://openalex.org/W2972799770","https://openalex.org/W3024869864","https://openalex.org/W3047941943","https://openalex.org/W3097777922","https://openalex.org/W3167533889","https://openalex.org/W3209984917","https://openalex.org/W4226390724","https://openalex.org/W4297841331","https://openalex.org/W4298333447","https://openalex.org/W4375850714","https://openalex.org/W4385245566","https://openalex.org/W4385823318","https://openalex.org/W4389315128","https://openalex.org/W4389315135","https://openalex.org/W6688816777","https://openalex.org/W6781745337"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"In":[0,73,91],"multi-speaker":[1],"scenarios,":[2],"automatic":[3],"speech":[4],"recognition":[5,55],"(ASR)":[6],"models":[7,25],"rely":[8],"on":[9,109],"pre-processed":[10],"audio":[11],"after":[12],"speaker":[13,19,48,54,86],"separation.":[14],"However,":[15],"when":[16,113],"the":[17,92,96,110,116,127,131],"target":[18,47,85],"is":[20],"not":[21],"accurately":[22],"separated,":[23],"ASR":[24,41,58],"face":[26],"limitations":[27],"in":[28,104,126],"reaching":[29],"their":[30],"peak":[31],"performance.":[32],"To":[33],"address":[34],"this":[35,74,120],"issue,":[36],"we":[37],"propose":[38],"a":[39,100],"speaker-adaptive":[40],"framework":[42,61,121],"that":[43],"possesses":[44],"more":[45],"implicit":[46],"enhancement":[49],"capability":[50],"by":[51],"efficiently":[52],"joint-optimized":[53],"(SR)":[56],"and":[57,69,83],"models.":[59],"Our":[60],"introduces":[62],"sharing":[63],"self-supervised":[64],"learning":[65],"representation,":[66],"optimization":[67],"transfer":[68],"hierarchy":[70],"speaker-gated":[71],"attention.":[72],"manner,":[75],"it":[76],"can":[77],"maximize":[78],"effectiveness":[79],"of":[80],"embedding":[81],"bias":[82],"emphasize":[84],"corresponding":[87],"to":[88,115],"semantic":[89],"units.":[90],"CHiME-7":[93,132],"DASR":[94],"sub-track,":[95],"proposed":[97],"method":[98],"achieves":[99],"28.19%":[101],"relative":[102],"reduction":[103],"word":[105],"error":[106],"rate":[107],"(WER)":[108],"development":[111],"sets":[112],"compared":[114],"official":[117],"baseline.":[118],"Notably,":[119],"has":[122],"also":[123],"been":[124],"employed":[125],"champion":[128],"system":[129],"for":[130],"DASR.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}