{"id":"https://openalex.org/W2980451698","doi":"https://doi.org/10.21437/interspeech.2019-1495","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":"2019-09-13","ids":{"openalex":"https://openalex.org/W2980451698","doi":"https://doi.org/10.21437/interspeech.2019-1495","mag":"2980451698"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1495","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","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":true,"raw_author_name":"Peidong Wang","raw_affiliation_strings":["Department of Computer Science and Engineer-ing, The Ohio State University, Columbus, OH 43210 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineer-ing, The Ohio State University, Columbus, OH 43210 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 Engineer-ing, The Ohio State University, Columbus, OH 43210 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineer-ing, The Ohio State University, Columbus, OH 43210 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":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210 USA","Department of Computer Science and Engineer-ing, The Ohio State University, Columbus, OH 43210 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineer-ing, The Ohio State University, Columbus, OH 43210 USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062250845"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"471","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976999759674072,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9573000073432922,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.9432752132415771},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.9030855894088745},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6691325902938843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6282820105552673},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5139774680137634},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49856138229370117},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.33741289377212524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2898011803627014},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12306061387062073},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.10837918519973755},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08773574233055115},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08525609970092773}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.9432752132415771},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.9030855894088745},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6691325902938843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6282820105552673},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5139774680137634},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49856138229370117},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.33741289377212524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2898011803627014},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12306061387062073},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.10837918519973755},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08773574233055115},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08525609970092773},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"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:10.21437/interspeech.2019-1495","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5501594644","display_name":"RI: Medium: Deep Neural Networks for Robust Speech Recognition through Integrated Acoustic Modeling and Separation","funder_award_id":"1409431","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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/G8570320909","display_name":"Deep neural networks for multi-channel speaker localization and speech separation","funder_award_id":"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"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1524333225","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/W2138939691","https://openalex.org/W2141411743","https://openalex.org/W2237671050","https://openalex.org/W2296167893","https://openalex.org/W2364134690","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/W2889442120","https://openalex.org/W2889698889","https://openalex.org/W2891644395","https://openalex.org/W2893370043","https://openalex.org/W2897371647","https://openalex.org/W2950258612","https://openalex.org/W2962866211","https://openalex.org/W2962998773","https://openalex.org/W2963122170","https://openalex.org/W2966212213","https://openalex.org/W4298998200"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1518859147","https://openalex.org/W2401567014","https://openalex.org/W2889698889","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W2275432853"],"abstract_inverted_index":{"Monaural":[0],"speech":[1,18,36,43,64,72,98,120],"enhancement":[2,55,65,77,121],"has":[3,19,44],"made":[4],"dramatic":[5],"advances":[6],"since":[7],"the":[8,60,76,83,110,125,130,137,142],"introduction":[9],"of":[10,53],"deep":[11],"learning":[12],"a":[13,92],"few":[14],"years":[15],"ago.Although":[16],"enhanced":[17],"been":[20],"demonstrated":[21],"to":[22,34,71,108],"have":[23],"better":[24],"intelligibility":[25],"and":[26,66,90],"quality":[27],"for":[28,96],"human":[29],"listeners,":[30],"feeding":[31],"it":[32],"directly":[33],"automatic":[35],"recognition":[37],"(ASR)":[38],"systems":[39],"trained":[40],"with":[41,119],"noisy":[42],"not":[45],"produced":[46],"expected":[47],"improvements":[48],"in":[49,75,133],"ASR":[50],"performance.The":[51],"lack":[52],"an":[54,113],"benefit":[56],"on":[57,141],"recognition,":[58,67],"or":[59],"gap":[61],"between":[62],"monaural":[63,97],"is":[68,106],"often":[69],"attributed":[70],"distortions":[73],"introduced":[74],"process.In":[78],"this":[79,134],"study,":[80],"we":[81],"analyze":[82],"distortion":[84,111],"problem,":[85],"compare":[86],"different":[87,123],"acoustic":[88,104,114],"models,":[89],"investigate":[91],"distortionindependent":[93],"training":[94],"scheme":[95],"recognition.Experimental":[99],"results":[100],"suggest":[101],"that":[102],"distortion-independent":[103],"modeling":[105],"able":[107],"overcome":[109],"problem.Such":[112],"model":[115],"can":[116],"also":[117],"work":[118],"models":[122,131],"from":[124],"one":[126],"used":[127],"during":[128],"training.Moreover,":[129],"investigated":[132],"paper":[135],"outperform":[136],"previous":[138],"best":[139],"system":[140],"CHiME-2":[143],"corpus.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}