{"id":"https://openalex.org/W3095545636","doi":"https://doi.org/10.21437/interspeech.2020-3139","title":"MultiSpeech: Multi-Speaker Text to Speech with Transformer","display_name":"MultiSpeech: Multi-Speaker Text to Speech with Transformer","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095545636","doi":"https://doi.org/10.21437/interspeech.2020-3139","mag":"3095545636"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3139","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5013803391","display_name":"Mingjian Chen","orcid":"https://orcid.org/0000-0003-0584-6286"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjian Chen","raw_affiliation_strings":["School of Software and Microelectronics, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"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,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]},{"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 Univeristy,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang Univeristy,","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698033","display_name":"Jin Xu","orcid":"https://orcid.org/0000-0001-5111-1286"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xu","raw_affiliation_strings":["Tsinghua University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037488877","display_name":"Hao Sun","orcid":"https://orcid.org/0000-0001-8456-7925"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["School of Software and Microelectronics, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software and Microelectronics, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Azure Speech","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","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,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4024","last_page":"4028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9699000120162964,"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":0.9531999826431274,"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/computer-science","display_name":"Computer science","score":0.6821152567863464},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6138814091682434},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5835371017456055},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.16860023140907288},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10409334301948547},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06508439779281616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6821152567863464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6138814091682434},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5835371017456055},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.16860023140907288},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10409334301948547},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06508439779281616}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-3139","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2767052532","https://openalex.org/W2808706139","https://openalex.org/W2886769154","https://openalex.org/W2903739847","https://openalex.org/W2940703732","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964243274","https://openalex.org/W2970079483","https://openalex.org/W2972677740","https://openalex.org/W2972702018","https://openalex.org/W4289383906","https://openalex.org/W4295731579","https://openalex.org/W4385245566","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W3157910026","https://openalex.org/W2892009249"],"abstract_inverted_index":{"Transformer-based":[0],"text":[1,44],"to":[2,25,91,119,130],"speech":[3,46,135],"(TTS)":[4],"model":[5,167,177],"(e.g.,":[6],"Transformer":[7,68,81,160],"TTS":[8,82],"[1],":[9],"FastSpeech":[10,176],"[2])":[11],"has":[12],"shown":[13],"the":[14,33,37,41,54,65,100,144,169],"advantages":[15],"of":[16,67,103,146],"training":[17,30,108],"and":[18,45,60,63,78,109,139,153],"inference":[19,187],"efficiency":[20],"over":[21],"Tacotron":[22],"[3])":[23],"due":[24],"its":[26],"parallel":[27,34],"computation":[28,35],"in":[29,47,53,106,117,127],"and/or":[31],"inference.However,":[32],"increases":[36],"difficulty":[38],"while":[39,183],"learning":[40],"alignment":[42],"between":[43,133],"Transformer,":[48],"which":[49],"is":[50],"further":[51],"magnified":[52],"multi-speaker":[55,70,141,156,175],"scenario":[56],"with":[57,86,164,178],"noisy":[58],"data":[59],"diverse":[61],"speakers,":[62],"hinders":[64],"applicability":[66],"for":[69],"TTS.In":[71],"this":[72],"paper,":[73],"we":[74,171],"develop":[75],"a":[76,96,125,165,173],"robust":[77,152],"high-quality":[79],"multispeaker":[80],"system":[83],"called":[84],"MultiSpeech,":[85],"several":[87],"specially":[88],"designed":[89],"components/techniques":[90],"improve":[92],"textto-speech":[93],"alignment:":[94],"1)":[95,148],"diagonal":[97],"constraint":[98],"on":[99,114,137],"weight":[101],"matrix":[102],"encoder-decoder":[104],"attention":[105],"both":[107],"inference;":[110],"2)":[111,163],"layer":[112],"normalization":[113],"phoneme":[115],"embedding":[116],"encoder":[118],"better":[120,154],"preserve":[121],"position":[122],"information;":[123],"3)":[124],"bottleneck":[126],"decoder":[128],"pre-net":[129],"prevent":[131],"copy":[132],"consecutive":[134],"frames.Experiments":[136],"VCTK":[138],"LibriTTS":[140],"datasets":[142],"demonstrate":[143],"effectiveness":[145],"MultiSpeech:":[147],"it":[149],"synthesizes":[150],"more":[151],"quality":[155,181],"voice":[157],"than":[158],"naive":[159],"based":[161],"TTS;":[162],"MutiSpeech":[166],"as":[168],"teacher,":[170],"obtain":[172],"strong":[174],"almost":[179],"zero":[180],"degradation":[182],"enjoying":[184],"extremely":[185],"fast":[186],"speed.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}