{"id":"https://openalex.org/W2972436155","doi":"https://doi.org/10.1109/taslp.2019.2946789","title":"Bridging the Gap Between Monaural Speech Enhancement and Recognition With Distortion-Independent Acoustic Modeling","display_name":"Bridging the Gap Between Monaural Speech Enhancement and Recognition With Distortion-Independent Acoustic Modeling","publication_year":2019,"publication_date":"2019-10-17","ids":{"openalex":"https://openalex.org/W2972436155","doi":"https://doi.org/10.1109/taslp.2019.2946789","mag":"2972436155"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2946789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2946789","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/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"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":"Peidong Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, USA"],"raw_orcid":"https://orcid.org/0000-0002-7042-0209","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058209019","display_name":"Ke Tan","orcid":"https://orcid.org/0000-0001-5073-8060"},"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":"Ke Tan","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, USA"],"raw_orcid":"https://orcid.org/0000-0001-5073-8060","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, 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":"De Liang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, 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":3.4356,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.93617822,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"28","issue":null,"first_page":"39","last_page":"48"},"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":0.9995999932289124,"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":0.9975000023841858,"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/monaural","display_name":"Monaural","score":0.981354832649231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7461292147636414},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7271485924720764},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6739469766616821},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6524330377578735},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6226184368133545},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5785720944404602},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5473610758781433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3189243674278259},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3185895085334778},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1678435206413269},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.1515413522720337},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0631721019744873}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.981354832649231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7461292147636414},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7271485924720764},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6739469766616821},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6524330377578735},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6226184368133545},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5785720944404602},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5473610758781433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3189243674278259},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3185895085334778},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1678435206413269},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.1515413522720337},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0631721019744873},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2946789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2946789","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":[],"awards":[{"id":"https://openalex.org/G7513161494","display_name":null,"funder_award_id":"ECCS-1808932","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8888347223","display_name":null,"funder_award_id":"IIS-1409431","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1524333225","https://openalex.org/W1598508708","https://openalex.org/W1897240248","https://openalex.org/W2023331723","https://openalex.org/W2035576074","https://openalex.org/W2044893557","https://openalex.org/W2057200980","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2101045344","https://openalex.org/W2121973264","https://openalex.org/W2138939691","https://openalex.org/W2141411743","https://openalex.org/W2237671050","https://openalex.org/W2296167893","https://openalex.org/W2364134690","https://openalex.org/W2397226255","https://openalex.org/W2398758402","https://openalex.org/W2399742709","https://openalex.org/W2403766732","https://openalex.org/W2405774341","https://openalex.org/W2408713104","https://openalex.org/W2516547830","https://openalex.org/W2550397165","https://openalex.org/W2678916739","https://openalex.org/W2888858245","https://openalex.org/W2889442120","https://openalex.org/W2889500840","https://openalex.org/W2889698889","https://openalex.org/W2891644395","https://openalex.org/W2893370043","https://openalex.org/W2897371647","https://openalex.org/W2962866211","https://openalex.org/W2962998773","https://openalex.org/W2963122170","https://openalex.org/W2966212213","https://openalex.org/W2980451698","https://openalex.org/W3147539069","https://openalex.org/W6631362777","https://openalex.org/W6639532686","https://openalex.org/W6680324615","https://openalex.org/W6689943771","https://openalex.org/W6712300757","https://openalex.org/W6712317276","https://openalex.org/W6712593814","https://openalex.org/W6713298849","https://openalex.org/W6713658392","https://openalex.org/W6713729801","https://openalex.org/W6726061053","https://openalex.org/W6754557777","https://openalex.org/W6766475400"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2037635165","https://openalex.org/W2513665862","https://openalex.org/W2231565466","https://openalex.org/W1505346162","https://openalex.org/W3042618827","https://openalex.org/W2120771489","https://openalex.org/W2034333290"],"abstract_inverted_index":{"Monaural":[0],"speech":[1,19,37,44,66,74,101,125],"enhancement":[2,57,67,79,126],"has":[3,20,45],"made":[4],"dramatic":[5],"advances":[6],"since":[7],"the":[8,62,78,86,114,130,136,143,148],"introduction":[9],"of":[10,55],"deep":[11],"learning":[12],"a":[13,95],"few":[14],"years":[15],"ago.":[16],"Although":[17],"enhanced":[18],"been":[21],"demonstrated":[22],"to":[23,35,73,112],"have":[24],"better":[25],"intelligibility":[26],"and":[27,68,93],"quality":[28],"for":[29,99],"human":[30],"listeners,":[31],"feeding":[32],"it":[33],"directly":[34],"automatic":[36],"recognition":[38],"(ASR)":[39],"systems":[40],"trained":[41],"with":[42,124],"noisy":[43],"not":[46],"produced":[47],"expected":[48],"improvements":[49],"in":[50,77,139],"ASR":[51],"performance.":[52],"The":[53],"lack":[54],"an":[56,118],"benefit":[58],"on":[59,147],"recognition,":[60,69],"or":[61],"gap":[63],"between":[64],"monaural":[65,100],"is":[70,110],"often":[71],"attributed":[72],"distortions":[75],"introduced":[76],"process.":[80],"In":[81],"this":[82,140],"article,":[83],"we":[84],"analyze":[85],"distortion":[87,115],"problem,":[88],"compare":[89],"different":[90,128],"acoustic":[91,108,119],"models,":[92],"investigate":[94],"distortion-independent":[96,107],"training":[97],"scheme":[98],"recognition.":[102],"Experimental":[103],"results":[104],"suggest":[105],"that":[106],"modeling":[109],"able":[111],"overcome":[113],"problem.":[116],"Such":[117],"model":[120],"can":[121],"also":[122],"work":[123],"models":[127,137],"from":[129],"one":[131],"used":[132],"during":[133],"training.":[134],"Moreover,":[135],"investigated":[138],"paper":[141],"outperform":[142],"previous":[144],"best":[145],"system":[146],"CHiME-2":[149],"corpus.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}