{"id":"https://openalex.org/W2787069756","doi":"https://doi.org/10.1109/asru.2017.8268914","title":"Adversarial training for data-driven speech enhancement without parallel corpus","display_name":"Adversarial training for data-driven speech enhancement without parallel corpus","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787069756","doi":"https://doi.org/10.1109/asru.2017.8268914","mag":"2787069756"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268914","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5101768343","display_name":"Takuya Higuchi","orcid":"https://orcid.org/0000-0002-0361-7132"},"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":"Takuya Higuchi","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"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":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"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 Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"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":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"47"},"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/T11447","display_name":"Blind Source Separation Techniques","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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.8339170217514038},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7529190182685852},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.7154799103736877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6903213858604431},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5832809805870056},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5547340512275696},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.4717579483985901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4631800949573517},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4618450999259949},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.43204864859580994},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42276692390441895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35852500796318054},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.20488354563713074},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0861096978187561}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8339170217514038},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7529190182685852},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7154799103736877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6903213858604431},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5832809805870056},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5547340512275696},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.4717579483985901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4631800949573517},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4618450999259949},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.43204864859580994},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42276692390441895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35852500796318054},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.20488354563713074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0861096978187561},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268914","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268914","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1548802052","https://openalex.org/W1563644625","https://openalex.org/W1799366690","https://openalex.org/W1897240248","https://openalex.org/W1987906574","https://openalex.org/W1992879732","https://openalex.org/W1995562189","https://openalex.org/W2013608223","https://openalex.org/W2024490156","https://openalex.org/W2027884847","https://openalex.org/W2031583051","https://openalex.org/W2033310064","https://openalex.org/W2096855653","https://openalex.org/W2099471712","https://openalex.org/W2100335648","https://openalex.org/W2104298926","https://openalex.org/W2135029798","https://openalex.org/W2140592340","https://openalex.org/W2141411743","https://openalex.org/W2144244295","https://openalex.org/W2185726469","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2402901296","https://openalex.org/W2404892923","https://openalex.org/W2405589348","https://openalex.org/W2407277936","https://openalex.org/W2506203739","https://openalex.org/W2586584460","https://openalex.org/W2640112133","https://openalex.org/W2699350432","https://openalex.org/W2963341071","https://openalex.org/W3143596294","https://openalex.org/W4205778870","https://openalex.org/W4302765731","https://openalex.org/W4320013936","https://openalex.org/W6633498727","https://openalex.org/W6638444622","https://openalex.org/W6680012447","https://openalex.org/W6713117669","https://openalex.org/W6713519970","https://openalex.org/W6743356167"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285","https://openalex.org/W1565692302"],"abstract_inverted_index":{"This":[0],"paper":[1,111],"describes":[2],"a":[3,20,26,43,54,70,78,87,102,113,120,162,186,231,235,240],"way":[4],"of":[5,58,86,90,135],"performing":[6],"data-driven":[7],"speech":[8,14,23,30,60,65,99,208],"enhancement":[9,24,31,209],"for":[10,22,46,49,67,119,127],"noise":[11],"robust":[12],"automatic":[13],"recognition":[15],"(ASR),":[16],"where":[17],"we":[18,52,82],"train":[19],"model":[21,50,72,106,128,142,232],"without":[25,108,185,203],"parallel":[27,55,187,205,236],"corpus.":[28,188],"Data-driven":[29],"with":[32,77,157,161,195,216,219,230,234],"deep":[33,71],"models":[34],"has":[35],"recently":[36],"been":[37],"investigated":[38],"and":[39,62,81,144,153,222],"proven":[40],"to":[41,170,179,227],"be":[42,74],"promising":[44],"approach":[45,115,210],"ASR.":[47],"However,":[48],"training,":[51],"need":[53],"corpus":[56,237],"consisting":[57],"noisy":[59,91],"signals":[61,66,152,155,221],"corresponding":[63,97],"clean":[64,98],"supervision.":[68,146],"Therefore":[69],"can":[73],"trained":[75,169,233],"only":[76],"simulated":[79],"dataset,":[80],"cannot":[83],"take":[84],"advantage":[85],"large":[88],"number":[89],"recordings":[92],"that":[93,228],"do":[94],"not":[95],"have":[96],"signals.":[100],"As":[101],"first":[103],"step":[104],"towards":[105],"training":[107,118,129],"supervision,":[109],"this":[110],"proposes":[112],"novel":[114],"introducing":[116],"adversarial":[117],"time-frequency":[121,158,183],"mask":[122,163,166,177],"estimator.":[123,164],"Our":[124],"cost":[125],"function":[126],"is":[130,168,192],"defined":[131],"by":[132,136],"discriminators":[133,148],"instead":[134],"using":[137],"the":[138,141,145,172,176,181],"distance":[139],"between":[140,150],"outputs":[143],"The":[147,165,189],"distinguish":[149],"true":[151],"enhanced":[154,190],"obtained":[156,194,218,229],"masks":[159,184],"estimated":[160],"estimator":[167,178],"cheat":[171],"discriminators,":[173],"which":[174],"enables":[175],"estimate":[180],"appropriate":[182],"signal":[191],"finally":[193],"masking-based":[196],"beamforming.":[197],"Experimental":[198],"results":[199,217],"show":[200],"that,":[201],"even":[202],"exploiting":[204],"data,":[206],"our":[207],"achieves":[211,223],"improved":[212],"ASR":[213,225],"performance":[214,226],"compared":[215],"unprocessed":[220],"comparable":[224],"based":[238],"on":[239],"minimum":[241],"mean":[242],"squared":[243],"error":[244],"(MMSE)":[245],"criterion.":[246]},"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":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}