{"id":"https://openalex.org/W2998616931","doi":"https://doi.org/10.1109/waspaa.2019.8937250","title":"Speech Enhancement Using End-to-End Speech Recognition Objectives","display_name":"Speech Enhancement Using End-to-End Speech Recognition Objectives","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2998616931","doi":"https://doi.org/10.1109/waspaa.2019.8937250","mag":"2998616931"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2019.8937250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5048730867","display_name":"Aswin Shanmugam Subramanian","orcid":"https://orcid.org/0000-0003-4446-001X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Shanmugam Subramanian","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100363470","display_name":"Xiaofei Wang","orcid":"https://orcid.org/0000-0002-7223-1030"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofei Wang","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064113992","display_name":"Murali Karthick Baskar","orcid":"https://orcid.org/0000-0002-9396-6319"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Karthick Baskar","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100862172","display_name":"Toru Taniguchi","orcid":"https://orcid.org/0000-0003-4984-2025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toru Taniguchi","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dung Tran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dung Tran","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Yahoo Japan Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"234","last_page":"238"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.836216926574707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7285446524620056},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7162767648696899},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6278587579727173},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5670953392982483},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5169350504875183},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4641287326812744},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.44118931889533997},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.4206511974334717},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4204466938972473},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3732351064682007},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33192265033721924},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24480760097503662},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07689014077186584},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07276111841201782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836216926574707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7285446524620056},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7162767648696899},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6278587579727173},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5670953392982483},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5169350504875183},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4641287326812744},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.44118931889533997},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.4206511974334717},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4204466938972473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3732351064682007},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33192265033721924},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24480760097503662},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07689014077186584},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07276111841201782},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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:10.1109/waspaa.2019.8937250","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W14578209","https://openalex.org/W1482149378","https://openalex.org/W1598508708","https://openalex.org/W1983812858","https://openalex.org/W2042141988","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2148613904","https://openalex.org/W2155027007","https://openalex.org/W2164502538","https://openalex.org/W2168729028","https://openalex.org/W2242685705","https://openalex.org/W2402901296","https://openalex.org/W2405774341","https://openalex.org/W2409483295","https://openalex.org/W2568308529","https://openalex.org/W2600628583","https://openalex.org/W2640112133","https://openalex.org/W2747732471","https://openalex.org/W2771275309","https://openalex.org/W2786835328","https://openalex.org/W2884797218","https://openalex.org/W2886180730","https://openalex.org/W2939497224","https://openalex.org/W2940526039","https://openalex.org/W2954695182","https://openalex.org/W2962780374","https://openalex.org/W2963127222","https://openalex.org/W2963197115","https://openalex.org/W2963351212","https://openalex.org/W4288366110","https://openalex.org/W4296927107","https://openalex.org/W6600580371","https://openalex.org/W6668037159","https://openalex.org/W6683204974","https://openalex.org/W6713117669","https://openalex.org/W6713658392","https://openalex.org/W6735168207","https://openalex.org/W6761289755","https://openalex.org/W6761806390","https://openalex.org/W6766380642"],"related_works":["https://openalex.org/W2963170046","https://openalex.org/W2376244802","https://openalex.org/W2923631784","https://openalex.org/W818226659","https://openalex.org/W4311414679","https://openalex.org/W2158075901","https://openalex.org/W2567141277","https://openalex.org/W3124036039","https://openalex.org/W2130785056","https://openalex.org/W2401089611"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,36,49,82,179],"systems,":[2],"which":[3,108],"denoise":[4],"and":[5,21,50,113,146,174,192],"dereverberate":[6],"distorted":[7],"signals,":[8],"are":[9],"usually":[10],"optimized":[11,73],"based":[12,74],"on":[13,75,84],"signal":[14,86,166],"reconstruction":[15],"objectives":[16,187],"including":[17],"the":[18,34,76,80,92,127,136,148,153,171],"maximum":[19],"likelihood":[20],"minimum":[22],"mean":[23],"square":[24],"error.":[25],"However,":[26],"emergent":[27],"end-to-end":[28,105,184],"neural":[29,110,120],"methods":[30],"enable":[31],"to":[32,68,91,125],"optimize":[33,47],"speech":[35,48,52,81,115,157,178],"system":[37,72],"with":[38,56,170],"more":[39],"application-oriented":[40],"objectives.":[41],"For":[42],"example,":[43],"we":[44,123],"can":[45,180],"jointly":[46],"automatic":[51],"recognition":[53,116],"(ASR)":[54],"only":[55],"ASR":[57,77,93,185],"error":[58,95],"minimization":[59],"criteria.":[60],"The":[61,160],"major":[62],"contribution":[63],"of":[64,131,155],"this":[65],"paper":[66],"is":[67],"investigate":[69],"how":[70,163],"a":[71,101,118,156],"objective":[78],"improves":[79],"quality":[83],"various":[85],"level":[87,167],"metrics":[88,168],"in":[89,139],"addition":[90],"word":[94],"rate":[96],"(WER)":[97],"metric.":[98],"We":[99],"use":[100],"recently":[102],"developed":[103],"multichannel":[104],"(ME2E)":[106],"system,":[107],"integrates":[109],"dereverberation,":[111],"beamforming,":[112],"attention-based":[114],"within":[117],"single":[119],"network.":[121],"Additionally,":[122],"propose":[124],"extend":[126,147],"dereverberation":[128],"sub":[129],"network":[130],"ME2E":[132],"by":[133,142,151,183],"dynamically":[134],"varying":[135],"filter":[137],"order":[138],"linear":[140],"prediction":[141],"using":[143,189],"reinforcement":[144],"learning,":[145],"beamforming":[149],"subnetwork":[150],"incorporating":[152],"estimation":[154],"distortion":[158],"factor.":[159],"experiments":[161],"reveal":[162],"well":[164],"different":[165],"correlate":[169],"WER":[172],"metric,":[173],"verify":[175],"that":[176],"learning-based":[177],"be":[181],"realized":[182],"training":[186],"without":[188],"parallel":[190],"clean":[191],"noisy":[193],"data.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}