{"id":"https://openalex.org/W4385823058","doi":"https://doi.org/10.21437/interspeech.2023-167","title":"Time-Domain Speech Enhancement for Robust Automatic Speech Recognition","display_name":"Time-Domain Speech Enhancement for Robust Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823058","doi":"https://doi.org/10.21437/interspeech.2023-167","pmid":"https://pubmed.ncbi.nlm.nih.gov/40313476"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-167","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12045131/pdf/nihms-2076298.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100563063","display_name":"Yufeng Yang","orcid":"https://orcid.org/0009-0000-1486-2144"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufeng Yang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687379","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3502-1595"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Center for Cognitive and Brain Sciences, The Ohio State University, USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2023","issue":null,"first_page":"4913","last_page":"4917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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":0.9959999918937683,"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":0.9936000108718872,"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/speech-recognition","display_name":"Speech recognition","score":0.7614781856536865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7500451803207397},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6086817383766174},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5291215181350708},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4383707344532013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39388900995254517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0686149001121521}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7614781856536865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7500451803207397},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6086817383766174},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5291215181350708},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4383707344532013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39388900995254517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0686149001121521},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-167","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmid:40313476","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40313476","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12045131","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12045131","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12045131/pdf/nihms-2076298.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:12045131","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12045131","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12045131/pdf/nihms-2076298.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G7332361580","display_name":"Category I: Bridges-2: Scalable Converged Computing, Data, and Analytics for Rapidly Evolving Science and Engineering Research","funder_award_id":"1928147","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8683737838","display_name":null,"funder_award_id":"ACI-1928147","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823058.pdf"},"referenced_works_count":0,"referenced_works":[],"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":{"It":[0],"has":[1,20,65],"been":[2,22],"shown":[3],"that":[4,113],"the":[5,55,109,132],"intelligibility":[6],"of":[7,57],"noisy":[8,35,44],"speech":[9,14,18,31,45,50,63,96,116],"can":[10],"be":[11],"improved":[12,119],"by":[13,135],"enhancement":[15,19,51,64,89,97],"algorithms.":[16],"However,":[17],"not":[21],"established":[23],"as":[24,62],"an":[25,39,82,99],"effective":[26],"frontend":[27],"for":[28],"robust":[29,58],"automatic":[30],"recognition":[32],"(ASR)":[33],"in":[34,69],"conditions":[36],"compared":[37],"to":[38,118],"ASR":[40,53,59,120],"model":[41,101],"trained":[42,102],"on":[43,77,104,108],"directly.":[46],"The":[47,91,122],"divide":[48,80],"between":[49],"and":[52,98],"impedes":[54],"progress":[56],"systems":[60],"especially":[61],"made":[66],"big":[67],"strides":[68],"recent":[70],"years.":[71],"In":[72],"this":[73,79],"work,":[74],"we":[75],"focus":[76],"eliminating":[78],"with":[81],"ARN":[83,114],"(attentive":[84],"recurrent":[85],"network)":[86],"based":[87],"time-domain":[88],"model.":[90],"proposed":[92,123],"system":[93,124],"fully":[94],"decouples":[95],"acoustic":[100],"only":[103],"clean":[105],"speech.":[106],"Results":[107],"CHiME-2":[110],"corpus":[111],"show":[112],"enhanced":[115],"translates":[117],"results.":[121],"achieves":[125],"6.28%":[126],"average":[127],"word":[128],"error":[129],"rate,":[130],"outperforming":[131],"previous":[133],"best":[134],"19.3%":[136],"relatively.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
