{"id":"https://openalex.org/W4319781852","doi":"https://doi.org/10.1109/iscslp57327.2022.10037914","title":"AccentSpeech: Learning Accent from Crowd-sourced Data for Target Speaker TTS with Accents","display_name":"AccentSpeech: Learning Accent from Crowd-sourced Data for Target Speaker TTS with Accents","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319781852","doi":"https://doi.org/10.1109/iscslp57327.2022.10037914"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037914","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10037914","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5060467975","display_name":"Yongmao Zhang","orcid":"https://orcid.org/0009-0000-0526-5778"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongmao Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106698700","display_name":"Zhichao Wang","orcid":"https://orcid.org/0000-0001-8075-1784"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichao Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","Tencent,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Tencent,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100563576","display_name":"Peiji Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiji Yang","raw_affiliation_strings":["Tencent,Shenzhen,China","Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015400213","display_name":"Hongshen Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongshen Sun","raw_affiliation_strings":["Tencent,Shenzhen,China","Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757049","display_name":"Zhisheng Wang","orcid":"https://orcid.org/0000-0001-6620-5883"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhisheng Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","Tencent,Shenzhen,China","Tencent, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Tencent,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4153,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60747416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"abs/2106.15561","issue":null,"first_page":"76","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.8021026849746704},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7764344215393066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7410587072372437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7176370620727539},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5049050450325012},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44038230180740356},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4345463514328003},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.4282693564891815},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4253312945365906},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41908252239227295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3628358244895935},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13864171504974365}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8021026849746704},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7764344215393066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7410587072372437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7176370620727539},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5049050450325012},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44038230180740356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4345463514328003},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.4282693564891815},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4253312945365906},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41908252239227295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628358244895935},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13864171504974365},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037914","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscslp57327.2022.10037914","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1991682319","https://openalex.org/W1992475611","https://openalex.org/W2017742648","https://openalex.org/W2122364000","https://openalex.org/W2518172956","https://openalex.org/W2890402938","https://openalex.org/W2904459034","https://openalex.org/W2964243274","https://openalex.org/W3007067948","https://openalex.org/W3015430779","https://openalex.org/W3022057435","https://openalex.org/W3024869864","https://openalex.org/W3097728852","https://openalex.org/W3104309246","https://openalex.org/W3135644023","https://openalex.org/W3146550708","https://openalex.org/W3174758275","https://openalex.org/W3197478142","https://openalex.org/W3198048667","https://openalex.org/W3203407300","https://openalex.org/W3203614938","https://openalex.org/W6631362777","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6763832098","https://openalex.org/W6783867762","https://openalex.org/W6796730497","https://openalex.org/W6803401863"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W2071315723","https://openalex.org/W2507083698","https://openalex.org/W2465473908","https://openalex.org/W4360877803","https://openalex.org/W49590631","https://openalex.org/W2474947928","https://openalex.org/W2967415048","https://openalex.org/W4301230705","https://openalex.org/W1489682032"],"abstract_inverted_index":{"Learning":[0],"accent":[1,19,48,84,125,187,217,238,262],"from":[2,142,232],"crowd-sourced":[3,117,138],"data":[4,41,46,118,172,206],"is":[5,75,134,178,230,240,256],"a":[6,11,65,78,86,157,174,204,259],"feasible":[7],"way":[8],"to":[9,29,53,82,90,108,156,185,215],"achieve":[10],"target":[12,44,128,170,221,235],"speaker":[13,45,92,129,171,222,236],"TTS":[14,70,74,261],"system":[15,122],"that":[16,105],"can":[17],"synthesize":[18],"speech.":[20],"To":[21,59,147,189],"this":[22,61,149],"end,":[23],"there":[24],"are":[25,106,140,165,201],"two":[26,183],"challenging":[27],"problems":[28],"be":[30],"solved.":[31],"First,":[32],"direct":[33,112],"use":[34],"of":[35,127],"the":[36,43,102,116,120,136,137,143,153,168,182,191,194,210,220,227,233,243,247],"poor":[37,131],"acoustic":[38],"quality":[39],"crowdsourced":[40],"and":[42,85,163,173,197,237],"in":[47,72,119,180,258],"transfer":[49,239,263],"will":[50,123],"apparently":[51],"lead":[52],"synthetic":[54],"speech":[55,126,218],"with":[56,130,223],"degraded":[57],"quality.":[58],"mitigate":[60],"problem,":[62,150],"we":[63,151],"take":[64],"bottleneck":[66],"feature":[67,99],"(BN)":[68],"based":[69,97],"approach,":[71,160,252],"which":[73],"decomposed":[76],"into":[77],"Text-to-BN":[79],"(T2BN)":[80],"module":[81,89,177,245],"learn":[83,91],"BN-to-Mel":[87],"(BN2Me1)":[88],"timbre,":[93],"where":[94,161],"neural":[95],"network":[96],"BN":[98,199],"serves":[100],"as":[101,226,254],"intermediate":[103],"representation":[104],"robust":[107],"noise":[109],"interference.":[110],"Second,":[111],"training":[113],"T2BN":[114,162],"using":[115,167],"two-stage":[121,154],"produce":[124,216],"prosody.":[132],"This":[133],"because":[135],"recordings":[139],"contributed":[141],"ordinary":[144],"unprofessional":[145],"speakers.":[146],"tackle":[148],"update":[152],"approach":[155,213],"novel":[158],"three-stage":[159,212],"BN2Me1":[164],"trained":[166],"high-quality":[169],"new":[175],"BN-to-BN":[176],"plugged":[179],"between":[181],"modules":[184],"perform":[186],"transfer.":[188],"train":[190],"BN2BN":[192,244],"module,":[193],"parallel":[195],"unaccented":[196],"accented":[198],"features":[200],"obtained":[202],"by":[203,242],"proposed":[205,211,251],"augmentation":[207],"procedure.":[208],"Finally":[209],"manages":[214],"for":[219],"good":[224],"prosody,":[225],"prosody":[228],"pattern":[229],"inherited":[231],"professional":[234],"achieved":[241],"at":[246],"same":[248],"time.":[249],"The":[250],"named":[253],"AccentSpeech,":[255],"validated":[257],"Mandarin":[260],"task.":[264]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}