{"id":"https://openalex.org/W2888858245","doi":"https://doi.org/10.21437/interspeech.2018-2409","title":"Cycle-Consistent Speech Enhancement","display_name":"Cycle-Consistent Speech Enhancement","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2888858245","doi":"https://doi.org/10.21437/interspeech.2018-2409","mag":"2888858245"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2409","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2409","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1809.02253","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":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Microsoft AI and Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110122094","display_name":"Biing-Hwang Juang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biing-Hwang (Fred) Juang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101749753"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":6.4714,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97461333,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1165","last_page":"1169"},"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":0.996999979019165,"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":0.9922999739646912,"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":0.8394348621368408},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7427922487258911},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5650706887245178},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5634028315544128},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5579156279563904},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5560864806175232},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4823576807975769},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46622565388679504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4523528218269348},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.44895777106285095},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44425442814826965},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44257721304893494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.440273255109787},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4228704869747162},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.41646355390548706},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2943726181983948},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.124370276927948}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8394348621368408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427922487258911},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5650706887245178},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5634028315544128},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5579156279563904},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5560864806175232},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4823576807975769},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46622565388679504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4523528218269348},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.44895777106285095},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44425442814826965},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44257721304893494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.440273255109787},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4228704869747162},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.41646355390548706},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2943726181983948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.124370276927948},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-2409","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2409","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:1809.02253","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.02253","pdf_url":"https://arxiv.org/pdf/1809.02253","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:1809.02253","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.02253","pdf_url":"https://arxiv.org/pdf/1809.02253","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W648143168","https://openalex.org/W1495679096","https://openalex.org/W1882958252","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/W2402040300","https://openalex.org/W2405774341","https://openalex.org/W2510867321","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/W2889500840","https://openalex.org/W2951523806","https://openalex.org/W2962793481","https://openalex.org/W2962879692","https://openalex.org/W2962894366","https://openalex.org/W2962896155","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","https://openalex.org/W4295521014","https://openalex.org/W4320013936","https://openalex.org/W4394670483"],"related_works":["https://openalex.org/W4287870380","https://openalex.org/W2401089611","https://openalex.org/W2022538999","https://openalex.org/W1955763106","https://openalex.org/W2002243964","https://openalex.org/W3090086172","https://openalex.org/W4375869276","https://openalex.org/W1603113134","https://openalex.org/W1585241115","https://openalex.org/W2120213246"],"abstract_inverted_index":{"Feature":[0],"mapping":[1,24,54],"using":[2,185,188],"deep":[3],"neural":[4],"networks":[5,92,137],"is":[6,56,70,83,100,109,131],"an":[7,51],"effective":[8],"approach":[9],"for":[10,133],"single-channel":[11],"speech":[12,46,98,193],"enhancement.":[13],"Noisy":[14],"features":[15,36,62,106,146],"are":[16,37,138,156],"transformed":[17],"to":[18,58,72,119,140],"the":[19,27,32,60,64,74,86,90,97,104,114,142,148,168,171],"enhanced":[20,33,65,105,143],"ones":[21],"through":[22,162],"a":[23,44,78],"network":[25,55,116],"and":[26,34,93,128,144,150,176,191],"mean":[28],"square":[29],"errors":[30],"between":[31],"clean":[35,129,149,190],"minimized.":[38],"In":[39,122],"this":[40],"paper,":[41],"we":[42],"propose":[43],"cycle-consistent":[45,68],"enhancement":[47],"(CSE)":[48],"in":[49,85,103],"which":[50],"additional":[52],"inverse":[53],"introduced":[57],"reconstruct":[59],"noisy":[61,127,151,192],"from":[63,147],"ones.":[66,152],"A":[67],"constraint":[69],"enforced":[71],"minimize":[73],"reconstruction":[75,160],"loss.":[76],"Similarly,":[77],"backward":[79],"cycle":[80],"of":[81],"mappings":[82],"performed":[84],"opposite":[87],"direction":[88],"with":[89,159],"same":[91],"losses.":[94],"With":[95],"cycle-consistency,":[96],"structure":[99],"well":[101],"preserved":[102],"while":[107],"noise":[108],"effectively":[110],"reduced":[111],"such":[112],"that":[113],"feature-mapping":[115],"generalizes":[117],"better":[118],"unseen":[120],"data.":[121,194],"cases":[123],"where":[124],"only":[125],"unparalleled":[126],"data":[130],"available":[132],"training,":[134],"two":[135],"discriminator":[136],"used":[139],"distinguish":[141],"noised":[145],"The":[153],"discrimination":[154],"losses":[155,161],"jointly":[157],"optimized":[158],"adversarial":[163],"multi-task":[164],"learning.":[165],"Evaluated":[166],"on":[167],"CHiME-3":[169],"dataset,":[170],"proposed":[172],"CSE":[173],"achieves":[174],"19.60%":[175],"6.69%":[177],"relative":[178],"word":[179],"error":[180],"rate":[181],"improvements":[182],"respectively":[183],"when":[184],"or":[186],"without":[187],"parallel":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}