{"id":"https://openalex.org/W4408353431","doi":"https://doi.org/10.1109/icassp49660.2025.10889737","title":"Reducing the Gap Between Pretrained Speech Enhancement and Recognition Models Using a Real Speech-Trained Bridging Module","display_name":"Reducing the Gap Between Pretrained Speech Enhancement and Recognition Models Using a Real Speech-Trained Bridging Module","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353431","doi":"https://doi.org/10.1109/icassp49660.2025.10889737"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5101445032","display_name":"Zhanfeng Cui","orcid":"https://orcid.org/0000-0002-9251-9752"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhongjian Cui","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114138967","display_name":"Chenrui Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenrui Cui","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106558173","display_name":"Tianrui Wang","orcid":"https://orcid.org/0000-0002-2765-5889"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Wang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110171247","display_name":"Mengnan He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengnan He","raw_affiliation_strings":["DiDi Chuxing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"DiDi Chuxing,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088361896","display_name":"Hao Shi","orcid":"https://orcid.org/0000-0003-3373-2147"},"institutions":[{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]},{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hao Shi","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Kyoto,Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Kyoto,Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103107663","display_name":"Meng Ge","orcid":"https://orcid.org/0000-0003-4251-0482"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Ge","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041513772","display_name":"Caixia Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caixia Gong","raw_affiliation_strings":["DiDi Chuxing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"DiDi Chuxing,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105269944","display_name":"Longbiao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101515499","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0003-4504-5758"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Chinese Academy of Sciences,Shenzhen Institute of Advanced Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shenzhen Institute of Advanced Technology,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101445032"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75568182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9939000010490417,"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":0.9939000010490417,"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":0.9882000088691711,"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/T12031","display_name":"Speech and dialogue systems","score":0.9609000086784363,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.9015719890594482},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7327120900154114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7224220037460327},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5733210444450378},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4202061891555786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32350531220436096},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07791844010353088}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.9015719890594482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7327120900154114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224220037460327},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5733210444450378},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4202061891555786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32350531220436096},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07791844010353088},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1992475611","https://openalex.org/W2042141988","https://openalex.org/W2296167893","https://openalex.org/W2398042854","https://openalex.org/W2640112133","https://openalex.org/W2760287881","https://openalex.org/W2794506738","https://openalex.org/W2803583024","https://openalex.org/W2928165649","https://openalex.org/W2936774411","https://openalex.org/W2952014059","https://openalex.org/W2962892438","https://openalex.org/W2964539095","https://openalex.org/W3096408984","https://openalex.org/W3140783160","https://openalex.org/W3211278025","https://openalex.org/W4221153233","https://openalex.org/W4224917453","https://openalex.org/W4225298533","https://openalex.org/W4225302959","https://openalex.org/W4226390724","https://openalex.org/W4297841603","https://openalex.org/W4372267368","https://openalex.org/W4379984888","https://openalex.org/W4391021775","https://openalex.org/W4391431556","https://openalex.org/W4392487628","https://openalex.org/W4392909067","https://openalex.org/W4392909789","https://openalex.org/W4399168695","https://openalex.org/W4400877621","https://openalex.org/W4401070302","https://openalex.org/W4402112631","https://openalex.org/W4404577030","https://openalex.org/W6847363464","https://openalex.org/W6856619237","https://openalex.org/W6869090967","https://openalex.org/W6996806968"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2981428355","https://openalex.org/W1834994814"],"abstract_inverted_index":{"The":[0,146,175],"information":[1],"loss":[2],"or":[3],"distortion":[4],"caused":[5],"by":[6,31,131],"single-channel":[7],"speech":[8,16,58,98],"enhancement":[9],"(SE)":[10],"harms":[11],"the":[12,38,44,51,79,92,103,109,120,123,132,141,160,171,179,184,193],"performance":[13,30],"of":[14,95,122],"automatic":[15],"recognition":[17],"(ASR).":[18],"Observation":[19],"addition":[20],"(OA)":[21],"is":[22,41,88,129,157,167],"an":[23],"effective":[24],"post-processing":[25],"method":[26],"to":[27,77,90,107,118,139,150,169],"improve":[28],"ASR":[29,133],"balancing":[32],"noisy":[33,57,68,84,97],"and":[34,166],"enhanced":[35],"speech.":[36,69,85],"Determining":[37],"OA":[39,47,137,173],"coefficient":[40,48],"crucial.":[42],"However,":[43],"currently":[45],"supervised":[46],"module,":[49,53,198],"called":[50],"bridging":[52,80,110,124,161,197],"only":[54],"utilizes":[55],"simulated":[56,194],"for":[59,102],"training,":[60],"which":[61],"has":[62],"a":[63,152],"severe":[64],"mismatch":[65],"with":[66,82,99,163,192],"real":[67,83,96,201],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"training":[75,115],"strategies":[76],"train":[78,108],"module":[81,125,162],"First,":[86],"DNSMOS":[87],"selected":[89],"evaluate":[91],"perceptual":[93],"quality":[94],"no":[100],"need":[101],"corresponding":[104],"clean":[105],"label":[106],"module.":[111],"Additional":[112],"constraints":[113],"during":[114],"are":[116,148],"introduced":[117,158],"enhance":[119],"robustness":[121],"further.":[126],"Each":[127],"utterance":[128],"evaluated":[130],"back-end":[134],"using":[135],"various":[136],"coefficients":[138],"obtain":[140],"word":[142],"error":[143],"rates":[144],"(WERs).":[145],"WERs":[147],"used":[149,168],"construct":[151],"multidimensional":[153],"vector.":[154],"This":[155],"vector":[156],"into":[159],"multi-task":[164],"learning":[165],"determine":[170],"optimal":[172],"coefficients.":[174],"experimental":[176],"results":[177],"on":[178],"CHiME-4":[180],"dataset":[181],"show":[182],"that":[183],"proposed":[185],"methods":[186],"all":[187],"had":[188],"significant":[189],"improvement":[190],"compared":[191],"data":[195],"trained":[196],"especially":[199],"under":[200],"evaluation":[202],"sets.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}