{"id":"https://openalex.org/W3163906773","doi":"https://doi.org/10.1109/icassp39728.2021.9413934","title":"Denoispeech: Denoising Text to Speech with Frame-Level Noise Modeling","display_name":"Denoispeech: Denoising Text to Speech with Frame-Level Noise Modeling","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163906773","doi":"https://doi.org/10.1109/icassp39728.2021.9413934","mag":"3163906773"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5120779464","display_name":"Chen Zhang","orcid":"https://orcid.org/0009-0004-3596-4683"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088179161","display_name":"Yi Ren","orcid":"https://orcid.org/0000-0001-9889-5460"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ren","raw_affiliation_strings":["Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101522530","display_name":"Xu Tan","orcid":"https://orcid.org/0000-0001-5631-0639"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Tan","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065126806","display_name":"Jinglin Liu","orcid":"https://orcid.org/0000-0002-9905-3887"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinglin Liu","raw_affiliation_strings":["Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577175","display_name":"Kejun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejun Zhang","raw_affiliation_strings":["Zhejiang University, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020025718","display_name":"Tao Qin","orcid":"https://orcid.org/0000-0002-9095-0776"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qin","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329353","display_name":"Sheng Zhao","orcid":"https://orcid.org/0000-0002-9624-5381"},"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":"Sheng Zhao","raw_affiliation_strings":["Microsoft Azure Speech"],"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101884287","display_name":"Tie\u2010Yan Liu","orcid":"https://orcid.org/0000-0002-0476-8020"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tie-Yan Liu","raw_affiliation_strings":["Microsoft Research Asia"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5120779464"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":4.4869,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.95389316,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7063","last_page":"7067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7907983064651489},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7768750190734863},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7001741528511047},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5932210683822632},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5816375017166138},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.545650064945221},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.5200214385986328},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5179997086524963},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.500279426574707},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4867725372314453},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.47355714440345764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41603603959083557},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05721259117126465}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7907983064651489},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7768750190734863},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7001741528511047},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5932210683822632},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5816375017166138},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.545650064945221},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.5200214385986328},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5179997086524963},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.500279426574707},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4867725372314453},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.47355714440345764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41603603959083557},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05721259117126465},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W2127141656","https://openalex.org/W2133665775","https://openalex.org/W2159202424","https://openalex.org/W2514828952","https://openalex.org/W2527729766","https://openalex.org/W2603567530","https://openalex.org/W2747874407","https://openalex.org/W2801554275","https://openalex.org/W2907262790","https://openalex.org/W2963341071","https://openalex.org/W2963568578","https://openalex.org/W2964121744","https://openalex.org/W2998161426","https://openalex.org/W3015338123","https://openalex.org/W3029282897","https://openalex.org/W3033411150","https://openalex.org/W3095883095","https://openalex.org/W3130016944","https://openalex.org/W3175871055","https://openalex.org/W4289383906","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6727697161","https://openalex.org/W6755300632","https://openalex.org/W6778215197","https://openalex.org/W6778823374","https://openalex.org/W6780274444"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4200596008","https://openalex.org/W596245619"],"abstract_inverted_index":{"While":[0],"neural-based":[1],"text":[2],"to":[3,22],"speech":[4,17,29,62,86,112,118,126],"(TTS)":[5],"models":[6],"can":[7,109],"synthesize":[8,110],"natural":[9],"and":[10,161],"intelligible":[11],"voice,":[12],"they":[13,82],"usually":[14,48,83],"require":[15],"high-quality":[16],"data,":[18],"which":[19,36,138],"is":[20,34,139],"costly":[21],"collect.":[23],"In":[24,99,120],"many":[25],"scenarios,":[26],"only":[27],"noisy":[28,79,117,125],"of":[30],"a":[31,70,105,114,134],"target":[32],"speaker":[33,115],"available,":[35],"presents":[37],"challenges":[38],"for":[39,43,113],"TTS":[40,58,106,144],"model":[41,59],"training":[42,56,77],"this":[44,100],"speaker.":[45],"Previous":[46],"works":[47],"address":[49],"the":[50,57,61,129,143,155],"challenge":[51],"using":[52,60],"two":[53,157],"methods:":[54],"1)":[55],"denoised":[63],"with":[64,78,87,94,116,133,142],"an":[65],"enhancement":[66],"model;":[67],"2)":[68],"taking":[69],"single":[71],"noise":[72,90,132,135],"embedding":[73],"as":[74,92],"input":[75],"when":[76],"speech.":[80],"However,":[81],"cannot":[84],"handle":[85,123],"real-world":[88,124,149],"complicated":[89],"such":[91],"those":[93],"high":[95],"variations":[96],"along":[97],"time.":[98],"paper,":[101],"we":[102,122],"develop":[103],"DenoiSpeech,":[104,121],"system":[107],"that":[108,152],"clean":[111],"data.":[119],"by":[127,159],"modeling":[128],"fine-grained":[130],"frame-level":[131],"condition":[136],"module,":[137],"jointly":[140],"trained":[141],"model.":[145],"Experimental":[146],"results":[147],"on":[148],"data":[150],"show":[151],"DenoiSpeech":[153],"outperforms":[154],"previous":[156],"methods":[158],"0.31":[160],"0.66":[162],"MOS":[163],"respectively.":[164],"<sup":[165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[167]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}