{"id":"https://openalex.org/W4391021717","doi":"https://doi.org/10.1109/asru57964.2023.10389724","title":"A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, And Extraction","display_name":"A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, And Extraction","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021717","doi":"https://doi.org/10.1109/asru57964.2023.10389724"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5087117512","display_name":"Kohei Saijo","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["JP","US"],"is_corresponding":true,"raw_author_name":"Kohei Saijo","raw_affiliation_strings":["Waseda University,Japan","Waseda University, Japan","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Carnegie Mellon University, USA","Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Waseda University,Japan","Waseda University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Waseda University,Japan","Waseda University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087117512"],"corresponding_institution_ids":["https://openalex.org/I150744194","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.6703,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85546198,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9980999827384949,"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":0.9919999837875366,"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":0.7600221037864685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.74237060546875},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6361120939254761},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6315803527832031},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5988174676895142},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5664626359939575},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5662848949432373},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5302198529243469},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5084115862846375},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.44848382472991943},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4428477883338928},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43326663970947266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3933151662349701},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3273777961730957},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1323666274547577},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12970006465911865},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1001732349395752},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.062121063470840454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600221037864685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.74237060546875},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6361120939254761},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6315803527832031},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5988174676895142},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5664626359939575},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5662848949432373},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5302198529243469},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5084115862846375},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.44848382472991943},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4428477883338928},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43326663970947266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3933151662349701},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3273777961730957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1323666274547577},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12970006465911865},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1001732349395752},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.062121063470840454},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1989314204","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2760103357","https://openalex.org/W2763188033","https://openalex.org/W2891054259","https://openalex.org/W2936302822","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2972767900","https://openalex.org/W2973062255","https://openalex.org/W2998657200","https://openalex.org/W3015199127","https://openalex.org/W3032969657","https://openalex.org/W3086154751","https://openalex.org/W3096730413","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3105169251","https://openalex.org/W3124972797","https://openalex.org/W3151851237","https://openalex.org/W3161301466","https://openalex.org/W3161934504","https://openalex.org/W3163652268","https://openalex.org/W3207860153","https://openalex.org/W4220731890","https://openalex.org/W4281820413","https://openalex.org/W4311000453","https://openalex.org/W4366503942","https://openalex.org/W4367597591","https://openalex.org/W4372271367","https://openalex.org/W6774995033","https://openalex.org/W6779752190","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,54,109,132],"multi-task":[3],"universal":[4],"speech":[5,13,19,61],"enhancement":[6,14],"(MUSE)":[7],"model":[8,72,91,100,125],"that":[9,45,57,121],"can":[10,126],"perform":[11,76],"five":[12,104],"(SE)":[15],"tasks:":[16],"dereverberation,":[17],"denoising,":[18],"separation":[20,43,65],"(SS),":[21],"target":[22,60,68,80],"speaker":[23,27,48,69,81],"extraction":[24],"(TSE),":[25],"and":[26,50,52,85,95],"counting.":[28],"This":[29],"is":[30,73,83],"achieved":[31],"by":[32],"integrating":[33],"two":[34],"modules":[35],"into":[36],"an":[37,41],"SE":[38],"model:":[39],"1)":[40],"internal":[42,64],"module":[44,56],"does":[46],"both":[47],"counting":[49],"separation;":[51],"2)":[53],"TSE":[55,77],"extracts":[58],"the":[59,63,79,90,99,103,122],"from":[62],"outputs":[66],"using":[67],"cues.":[70],"The":[71],"trained":[74],"to":[75,92,101],"if":[78],"cue":[82],"given":[84],"SS":[86],"otherwise.":[87],"By":[88],"training":[89],"remove":[93],"noise":[94],"reverberation,":[96],"we":[97],"allow":[98],"tackle":[102],"tasks":[105,130],"mentioned":[106],"above":[107],"with":[108,131],"single":[110,133],"model,":[111],"which":[112],"has":[113],"not":[114],"been":[115],"accomplished":[116],"yet.":[117],"Evaluation":[118],"results":[119],"demonstrate":[120],"proposed":[123],"MUSE":[124],"successfully":[127],"handle":[128],"multiple":[129],"model.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-05T09:01:59.212387","created_date":"2025-10-10T00:00:00"}