{"id":"https://openalex.org/W4382203020","doi":"https://doi.org/10.1109/taslp.2023.3288418","title":"Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information","display_name":"Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4382203020","doi":"https://doi.org/10.1109/taslp.2023.3288418"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3288418","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3288418","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10164201.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10164201.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067198078","display_name":"Yen-Ju Lu","orcid":"https://orcid.org/0000-0001-8400-4188"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yen-Ju Lu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009566669","display_name":"Chia\u2010Yu Chang","orcid":"https://orcid.org/0000-0002-7020-8451"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Yu Chang","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058798840","display_name":"Cheng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng Yu","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066322070","display_name":"Ching\u2010Feng Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136334","display_name":"Chi Mei Medical Center","ror":"https://ror.org/02y2htg06","country_code":"TW","type":"healthcare","lineage":["https://openalex.org/I4210136334"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ching-Feng Liu","raw_affiliation_strings":["Chi Mei Hospital, Tainan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Chi Mei Hospital, Tainan, Taiwan","institution_ids":["https://openalex.org/I4210136334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeih-weih Hung","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Puli, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Puli, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"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":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5067198078"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":0.7942,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70451869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"2738","last_page":"2750"},"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":0.9994999766349792,"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":0.996999979019165,"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":0.8060711622238159},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7339361310005188},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5546872019767761},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48530668020248413},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.425005704164505},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.42227545380592346},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4218709170818329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3396494388580322},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.30014967918395996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060711622238159},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7339361310005188},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5546872019767761},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48530668020248413},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.425005704164505},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42227545380592346},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4218709170818329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3396494388580322},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.30014967918395996},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3288418","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3288418","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10164201.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3288418","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3288418","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10164201.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382203020.pdf","grobid_xml":"https://content.openalex.org/works/W4382203020.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1897240248","https://openalex.org/W1952003395","https://openalex.org/W1963950237","https://openalex.org/W1992475611","https://openalex.org/W2006129368","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2078844899","https://openalex.org/W2102898380","https://openalex.org/W2114338548","https://openalex.org/W2126505708","https://openalex.org/W2136586452","https://openalex.org/W2144404214","https://openalex.org/W2296167893","https://openalex.org/W2402901296","https://openalex.org/W2405774341","https://openalex.org/W2517760955","https://openalex.org/W2527611302","https://openalex.org/W2550397165","https://openalex.org/W2594607416","https://openalex.org/W2746457594","https://openalex.org/W2766219058","https://openalex.org/W2787921141","https://openalex.org/W2788241093","https://openalex.org/W2890820256","https://openalex.org/W2935934262","https://openalex.org/W2937525188","https://openalex.org/W2962998773","https://openalex.org/W2964227577","https://openalex.org/W2969649301","https://openalex.org/W2972320711","https://openalex.org/W2972443522","https://openalex.org/W2972481755","https://openalex.org/W2972542211","https://openalex.org/W2998616931","https://openalex.org/W3014522660","https://openalex.org/W3015219411","https://openalex.org/W3015312544","https://openalex.org/W3016132433","https://openalex.org/W3017350693","https://openalex.org/W3094932283","https://openalex.org/W3096408984","https://openalex.org/W3096442105","https://openalex.org/W3096567388","https://openalex.org/W3109196171","https://openalex.org/W3127686677","https://openalex.org/W3132954452","https://openalex.org/W3163827866","https://openalex.org/W3165858867","https://openalex.org/W3197284240","https://openalex.org/W4200634567","https://openalex.org/W4214567298","https://openalex.org/W4226339160","https://openalex.org/W4296070384","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6739901393","https://openalex.org/W6742802039","https://openalex.org/W6780226713","https://openalex.org/W6789826613","https://openalex.org/W6790758941","https://openalex.org/W6805434863"],"related_works":["https://openalex.org/W1630865680","https://openalex.org/W2373767407","https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W3034789145","https://openalex.org/W4367628250","https://openalex.org/W383418545","https://openalex.org/W197907117"],"abstract_inverted_index":{"Previous":[0],"studies":[1],"have":[2],"confirmed":[3,119],"that":[4,78,120,137,145,172],"by":[5,67,151],"augmenting":[6],"acoustic":[7],"features":[8],"with":[9,92,132,138,147],"the":[10,15,25,30,45,64,80,99,128,133,139,152,174,179,184,190],"place/manner":[11],"of":[12,29,48,82,149],"articulatory":[13,49],"features,":[14],"speech":[16,32,74,110,112,116],"enhancement":[17,35,117],"(SE)":[18],"process":[19],"can":[20,187],"be":[21,163],"guided":[22],"to":[23,36,54,62,97,157],"consider":[24],"broad":[26,83],"phonetic":[27,84,176],"properties":[28],"input":[31],"when":[33,182],"performing":[34],"attain":[37],"performance":[38,66],"improvements.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,60],"explore":[44],"contextual":[46,121],"information":[47,53,123],"attributes":[50],"as":[51],"additional":[52,185],"further":[55],"benefit":[56],"SE.":[57],"More":[58],"specifically,":[59],"propose":[61],"improve":[63,189],"SE":[65,100,125,129,191],"leveraging":[68],"losses":[69,96],"from":[70,109],"an":[71],"end-to-end":[72],"automatic":[73],"recognition":[75],"(E2E-ASR)":[76],"model":[77,130],"predicts":[79],"sequence":[81],"classes":[85],"(BPCs).":[86],"We":[87],"also":[88],"developed":[89],"multi-objective":[90],"training":[91],"ASR":[93,153],"and":[94,114,160],"perceptual":[95],"train":[98],"system":[101,154],"based":[102],"on":[103],"a":[104,164],"BPC-based":[105,134],"E2E-ASR.":[106,141],"Experimental":[107],"results":[108,143],"denoising,":[111],"dereverberation,":[113],"impaired":[115],"tasks":[118],"BPC":[122,161,181],"improves":[124],"performance.":[126,192],"Moreover,":[127],"trained":[131],"E2E-ASR":[135],"outperforms":[136],"phoneme-based":[140],"The":[142],"suggest":[144],"objectives":[146],"misclassification":[148],"phonemes":[150],"may":[155],"lead":[156],"imperfect":[158],"feedback,":[159],"could":[162],"potentially":[165],"better":[166],"choice.":[167],"Finally,":[168],"it":[169],"is":[170],"noted":[171],"combining":[173],"most-confusable":[175],"targets":[177],"into":[178],"same":[180],"calculating":[183],"objective":[186],"effectively":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}