{"id":"https://openalex.org/W2889500840","doi":"https://doi.org/10.21437/interspeech.2018-2461","title":"Adversarial Feature-Mapping for Speech Enhancement","display_name":"Adversarial Feature-Mapping for Speech Enhancement","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889500840","doi":"https://doi.org/10.21437/interspeech.2018-2461","mag":"2889500840"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2461","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.02251","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070867959","display_name":"Biing\u2010Hwang Juang","orcid":"https://orcid.org/0000-0002-5773-5679"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biing-Hwang (Fred) Juang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.4109,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.96909068,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3259","last_page":"3263"},"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":0.9966999888420105,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.9681835174560547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7458545565605164},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7418857216835022},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5434187054634094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5248082876205444},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5071170330047607},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48418310284614563},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48092982172966003},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4339791238307953},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14481675624847412}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9681835174560547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458545565605164},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7418857216835022},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5434187054634094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5248082876205444},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5071170330047607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48418310284614563},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48092982172966003},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4339791238307953},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14481675624847412},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-2461","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1809.02251","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.02251","pdf_url":"https://arxiv.org/pdf/1809.02251","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1809.02251","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.02251","pdf_url":"https://arxiv.org/pdf/1809.02251","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W648143168","https://openalex.org/W1489537150","https://openalex.org/W1495679096","https://openalex.org/W1897240248","https://openalex.org/W1973681148","https://openalex.org/W1984541135","https://openalex.org/W1992475611","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2076794394","https://openalex.org/W2094461119","https://openalex.org/W2099471712","https://openalex.org/W2141411743","https://openalex.org/W2160815625","https://openalex.org/W2289394825","https://openalex.org/W2290318471","https://openalex.org/W2293634267","https://openalex.org/W2296748324","https://openalex.org/W2405774341","https://openalex.org/W2510867321","https://openalex.org/W2584667682","https://openalex.org/W2587088898","https://openalex.org/W2608338293","https://openalex.org/W2636483419","https://openalex.org/W2735006420","https://openalex.org/W2749588430","https://openalex.org/W2769025471","https://openalex.org/W2774848319","https://openalex.org/W2787133659","https://openalex.org/W2795867901","https://openalex.org/W2796339975","https://openalex.org/W2888858245","https://openalex.org/W2962793481","https://openalex.org/W2962894366","https://openalex.org/W2963073614","https://openalex.org/W2963226019","https://openalex.org/W2963266252","https://openalex.org/W2963321191","https://openalex.org/W2963341071","https://openalex.org/W2963684088","https://openalex.org/W2963826681","https://openalex.org/W3112742522"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W2547793174","https://openalex.org/W2132885390","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817"],"abstract_inverted_index":{"Feature-mapping":[0],"with":[1,60,138],"deep":[2],"neural":[3],"networks":[4,81,143],"is":[5,28,67,102,126,135],"commonly":[6],"used":[7],"for":[8,52],"single-channel":[9],"speech":[10,53],"enhancement,":[11],"in":[12,129,150],"which":[13,55,130],"a":[14],"feature-mapping":[15,49,58,88,140,181],"network":[16,66,134],"directly":[17],"transforms":[18],"the":[19,23,32,37,57,71,75,87,93,99,108,139,146,153,158,161,175,180,185,193],"noisy":[20,177],"features":[21,73,101,110],"to":[22,30,69,85,144,152],"corresponding":[24],"enhanced":[25,38,72,100],"ones":[26],"and":[27,39,90,141,166,179,184],"trained":[29,137],"minimize":[31,86],"mean":[33],"square":[34],"errors":[35],"between":[36],"clean":[40,77,109],"features.":[41],"In":[42],"this":[43,112],"paper,":[44],"we":[45],"propose":[46],"an":[47,131],"adversarial":[48,61,113],"(AFM)":[50],"method":[51],"enhancement":[54],"advances":[56],"approach":[59],"learning.":[62],"An":[63],"additional":[64],"discriminator":[65,142],"introduced":[68],"distinguish":[70],"from":[74],"real":[76,176],"ones.":[78],"The":[79,96],"two":[80],"are":[82],"jointly":[83,136],"optimized":[84],"loss":[89,149],"simultaneously":[91],"mini-maximize":[92],"discrimination":[94],"loss.":[95],"distribution":[97],"of":[98,107],"further":[103,127],"pushed":[104],"towards":[105],"that":[106],"through":[111],"multi-task":[114],"training.":[115],"To":[116],"achieve":[117],"better":[118],"performance":[119],"on":[120,157],"ASR":[121],"task,":[122],"senone-aware":[123],"(SA)":[124],"AFM":[125,154,163],"proposed":[128,162],"acoustic":[132,195],"model":[133],"optimize":[145],"senone":[147],"classification":[148],"addition":[151],"losses.":[155],"Evaluated":[156],"CHiME-3":[159],"dataset,":[160],"achieves":[164,187],"16.95%":[165],"5.27%":[167],"relative":[168,189],"word":[169],"error":[170],"rate":[171],"(WER)":[172],"improvements":[173],"over":[174,192],"data":[178],"baseline":[182],"respectively":[183],"SA-AFM":[186],"9.85%":[188],"WER":[190],"improvement":[191],"multi-conditional":[194],"model.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}