{"id":"https://openalex.org/W4400877621","doi":"https://doi.org/10.1109/taslp.2024.3426924","title":"Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance","display_name":"Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400877621","doi":"https://doi.org/10.1109/taslp.2024.3426924"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3426924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426924","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Corporation, Chiyoda-ku, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Chiyoda-ku, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108670604","display_name":"Kazuma Iwamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuma Iwamoto","raw_affiliation_strings":["Doshisha Univer sity, Kyotanabe, Japan"],"affiliations":[{"raw_affiliation_string":"Doshisha Univer sity, Kyotanabe, Japan","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation, Chiyoda-ku, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Chiyoda-ku, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084590882","display_name":"Rintaro Ikeshita","orcid":"https://orcid.org/0000-0003-2608-1999"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rintaro Ikeshita","raw_affiliation_strings":["NTT Corporation, Chiyoda-ku, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Chiyoda-ku, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101739550","display_name":"Hiroshi Sato","orcid":"https://orcid.org/0000-0001-6575-0396"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation, Chiyoda-ku, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Chiyoda-ku, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Corporation, Chiyoda-ku, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Chiyoda-ku, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027443847","display_name":"Shigeru Katagiri","orcid":"https://orcid.org/0000-0003-4738-5385"},"institutions":[{"id":"https://openalex.org/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeru Katagiri","raw_affiliation_strings":["Doshisha Univer sity, Kyotanabe, Japan"],"affiliations":[{"raw_affiliation_string":"Doshisha Univer sity, Kyotanabe, Japan","institution_ids":["https://openalex.org/I133984924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5070624983"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":3.8008,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94217417,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"3589","last_page":"3602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9156000018119812,"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":0.9156000018119812,"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/speech-recognition","display_name":"Speech recognition","score":0.7463757395744324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6333717107772827},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5823915600776672},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4912366271018982},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4592023491859436},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38838058710098267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3325963616371155},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10597285628318787}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7463757395744324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6333717107772827},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5823915600776672},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4912366271018982},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4592023491859436},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38838058710098267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3325963616371155},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10597285628318787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3426924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3426924","pdf_url":null,"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":null,"license_id":null,"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":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1946152311","https://openalex.org/W1983108229","https://openalex.org/W2024490156","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2153384885","https://openalex.org/W2160815625","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2296167893","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2514741789","https://openalex.org/W2559260703","https://openalex.org/W2559809918","https://openalex.org/W2803583024","https://openalex.org/W2884797218","https://openalex.org/W2898268964","https://openalex.org/W2900212944","https://openalex.org/W2919115771","https://openalex.org/W2937484199","https://openalex.org/W2937998856","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962892438","https://openalex.org/W2962970934","https://openalex.org/W2964058413","https://openalex.org/W2972412503","https://openalex.org/W2981022124","https://openalex.org/W3015312544","https://openalex.org/W3032969657","https://openalex.org/W3086154751","https://openalex.org/W3095717210","https://openalex.org/W3096090308","https://openalex.org/W3099330747","https://openalex.org/W3104196160","https://openalex.org/W3163217847","https://openalex.org/W3185389098","https://openalex.org/W3198667862","https://openalex.org/W3209984917","https://openalex.org/W3211278025","https://openalex.org/W3213240302","https://openalex.org/W4221153233","https://openalex.org/W4224920397","https://openalex.org/W4226390724","https://openalex.org/W4293363567","https://openalex.org/W4296068829","https://openalex.org/W4297841603","https://openalex.org/W4367597591","https://openalex.org/W4384160435","https://openalex.org/W4392909789","https://openalex.org/W6601563604","https://openalex.org/W6631362777","https://openalex.org/W6638545294","https://openalex.org/W6782120700","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W3135230428","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2904739811","https://openalex.org/W2051376034","https://openalex.org/W2275432853","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"It":[0],"is":[1,21],"challenging":[2],"to":[3,24,51,124,150,224,257],"improve":[4,204,259],"automatic":[5],"speech":[6,16],"recognition":[7],"(ASR)":[8],"performance":[9,44,63,148,171],"in":[10,56,85,246],"noisy":[11],"conditions":[12],"with":[13,159,229],"a":[14,57,74,93,160,211],"single-channel":[15,34,53,252],"enhancement":[17],"(SE)":[18],"front-end.":[19],"This":[20,106,156],"generally":[22],"attributed":[23],"the":[25,30,38,81,99,110,113,127,139,151,169,181,190,198,205,222,226,239],"processing":[26,32,165],"distortions":[27,166],"caused":[28,250],"by":[29,251],"nonlinear":[31],"of":[33,40,83,103,112,129,143,154,164,183],"SE":[35,54,104,253],"front-ends.":[36],"However,":[37],"causes":[39],"such":[41],"degraded":[42],"ASR":[43,62,86,134,147,170,260],"have":[45],"not":[46],"been":[47],"fully":[48],"investigated.":[49],"How":[50],"design":[52],"front-ends":[55],"way":[58],"that":[59,78,167,189,237],"significantly":[60,258],"improves":[61],"remains":[64],"an":[65],"open":[66],"research":[67],"question.":[68],"In":[69],"this":[70,89],"study,":[71],"we":[72,91,174,187,209,235],"investigate":[73],"signal-level":[75],"numerical":[76],"metric":[77],"can":[79,203],"explain":[80],"cause":[82,168],"degradation":[84],"performance.":[87,135,261],"To":[88],"end,":[90],"propose":[92,210],"novel":[94,212],"analysis":[95,137],"scheme":[96,107],"based":[97],"on":[98,133,146],"orthogonal":[100],"projection-based":[101],"decomposition":[102],"errors.":[105,155,185,232],"manually":[108],"modifies":[109],"ratio":[111,218],"decomposed":[114],"interference,":[115],"noise,":[116],"and":[117,120,200,241],"artifact":[118,144,184,231,248],"errors,":[119],"it":[121],"enables":[122],"us":[123,158],"directly":[125],"evaluate":[126],"impact":[128,182],"each":[130],"error":[131],"type":[132],"Our":[136],"reveals":[138],"particularly":[140],"detrimental":[141],"effect":[142],"errors":[145,249],"compared":[149],"other":[152],"types":[153],"provides":[157],"more":[161],"principled":[162],"definition":[163],"degradation.":[172],"Then,":[173],"study":[175],"two":[176],"practical":[177],"approaches":[178,243],"for":[179],"reducing":[180],"First,":[186],"prove":[188],"simple":[191],"observation":[192],"adding":[193],"(OA)":[194],"post-processing":[195],"(i.e.,":[196],"interpolating":[197],"enhanced":[199,227],"observed":[201],"signals)":[202],"signal-to-artifact":[206],"ratio.":[207],"Second,":[208],"training":[213],"objective,":[214],"called":[215],"artifact-boosted":[216],"signal-to-distortion":[217],"(AB-SDR),":[219],"which":[220],"forces":[221],"model":[223],"estimate":[225],"signals":[228],"fewer":[230],"Through":[233],"experiments,":[234],"confirm":[236],"both":[238],"OA":[240],"AB-SDR":[242],"are":[244],"effective":[245],"decreasing":[247],"front-ends,":[254],"allowing":[255],"them":[256]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
