{"id":"https://openalex.org/W4319779739","doi":"https://doi.org/10.1109/iscslp57327.2022.10038135","title":"Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis","display_name":"Style-Label-Free: Cross-Speaker Style Transfer by Quantized VAE and Speaker-wise Normalization in Speech Synthesis","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319779739","doi":"https://doi.org/10.1109/iscslp57327.2022.10038135"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038135","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/A5028353824","display_name":"Chunyu Qiang","orcid":"https://orcid.org/0009-0007-2290-3074"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Qiang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101863403","display_name":"Peng Yang","orcid":"https://orcid.org/0009-0005-3449-5843"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Yang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112489758","display_name":"Hao Che","orcid":"https://orcid.org/0009-0001-9852-320X"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Che","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"institutions":[{"id":"https://openalex.org/I2801745840","display_name":"Kwai Chung Hospital","ror":"https://ror.org/05kz7bw59","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2801745840"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyuan Wang","raw_affiliation_strings":["Kwai,Beijing,P.R. China","Kwai, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwai,Beijing,P.R. China","institution_ids":["https://openalex.org/I2801745840"]},{"raw_affiliation_string":"Kwai, Beijing, P.R. China","institution_ids":["https://openalex.org/I2801745840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2801745840"],"apc_list":null,"apc_paid":null,"fwci":0.4152,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60731513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9962000250816345,"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":0.7319750189781189},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7174723744392395},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6683494448661804},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6639492511749268},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6527789831161499},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6089045405387878},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.44457441568374634},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4436027705669403},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4137316048145294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40066462755203247},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3562318682670593},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3448820114135742},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14463680982589722}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7319750189781189},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174723744392395},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6683494448661804},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6639492511749268},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6527789831161499},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6089045405387878},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.44457441568374634},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4436027705669403},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4137316048145294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40066462755203247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3562318682670593},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3448820114135742},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14463680982589722},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10038135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038135","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":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2187089797","https://openalex.org/W2752782242","https://openalex.org/W2752796333","https://openalex.org/W2795109282","https://openalex.org/W2901997113","https://openalex.org/W2904459034","https://openalex.org/W2932022923","https://openalex.org/W2963609956","https://openalex.org/W2963799213","https://openalex.org/W2996573371","https://openalex.org/W3015440759","https://openalex.org/W3026874504","https://openalex.org/W3081488690","https://openalex.org/W3083565479","https://openalex.org/W3094785744","https://openalex.org/W3096457008","https://openalex.org/W3133185996","https://openalex.org/W3135418837","https://openalex.org/W3135644023","https://openalex.org/W3139170550","https://openalex.org/W3161296985","https://openalex.org/W3163573274","https://openalex.org/W3163906773","https://openalex.org/W3174482005","https://openalex.org/W3194613004","https://openalex.org/W3195366750","https://openalex.org/W3198104520","https://openalex.org/W3206725777","https://openalex.org/W4289383906","https://openalex.org/W4311415873","https://openalex.org/W4319586674","https://openalex.org/W6637618735","https://openalex.org/W6640963894","https://openalex.org/W6748573829","https://openalex.org/W6750489868","https://openalex.org/W6755300632","https://openalex.org/W6756197946","https://openalex.org/W6757422803","https://openalex.org/W6760861152","https://openalex.org/W6762643587","https://openalex.org/W6768443183","https://openalex.org/W6768830310","https://openalex.org/W6777694618","https://openalex.org/W6779871621","https://openalex.org/W6791022691","https://openalex.org/W6798007402","https://openalex.org/W6802591955","https://openalex.org/W6810295262"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2134501921","https://openalex.org/W2125642021","https://openalex.org/W2144470400"],"abstract_inverted_index":{"Cross-speaker":[0],"style":[1,10,29,50,57,66,80,87,108,116],"transfer":[2,51,58],"in":[3],"speech":[4,16],"synthesis":[5],"aims":[6],"at":[7],"transferring":[8],"a":[9,18,48,69,90,115,136],"from":[11,59],"source":[12,60,100],"speaker":[13,61,64,101],"to":[14,42,62,84,97,105],"synthesised":[15],"of":[17,111],"target":[19,63],"speaker\u2019s":[20],"timbre.":[21],"Most":[22],"previous":[23],"approaches":[24],"rely":[25],"on":[26,74],"data":[27,120],"with":[28,138],"labels,":[30],"but":[31],"manually-annotated":[32],"labels":[33],"are":[34],"expensive":[35],"and":[36,79,118],"not":[37],"always":[38],"reliable.":[39],"In":[40,103],"response":[41],"this":[43],"problem,":[44],"we":[45],"propose":[46],"Style-Label-Free,":[47],"cross-speaker":[49],"method,":[52],"which":[53],"can":[54],"realize":[55],"the":[56,99,107,112,129,132],"without":[65],"labels.":[67],"Firstly,":[68],"reference":[70,113],"encoder":[71],"structure":[72],"based":[73],"quantized":[75],"variational":[76],"autoencoder":[77],"(Q-VAE)":[78],"bottleneck":[81],"is":[82,95,123],"designed":[83],"extract":[85],"discrete":[86],"representations.":[88],"Secondly,":[89],"speaker-wise":[91],"batch":[92],"normalization":[93],"layer":[94],"proposed":[96],"reduce":[98],"leakage.":[102],"order":[104],"improve":[106],"extraction":[109],"ability":[110],"encoder,":[114],"invariant":[117],"contrastive":[119],"augmentation":[121],"method":[122,130],"proposed.":[124],"Experimental":[125],"results":[126],"show":[127],"that":[128],"outperforms":[131],"baseline.":[133],"We":[134],"provide":[135],"website":[137],"audio":[139],"samples":[140],"<sup":[141],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[142],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[143],".":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}