{"id":"https://openalex.org/W4385822757","doi":"https://doi.org/10.21437/interspeech.2023-1151","title":"Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge","display_name":"Interpretable Style Transfer for Text-to-Speech with ControlVAE and Diffusion Bridge","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822757","doi":"https://doi.org/10.21437/interspeech.2023-1151"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1151","doi":"https://doi.org/10.21437/interspeech.2023-1151","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1151","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"INTERSPEECH 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.04301","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111310824","display_name":"Wenhao Guan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Guan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455323","display_name":"Tao Li","orcid":"https://orcid.org/0000-0002-6239-969X","observed_orcids":["https://orcid.org/0000-0002-6239-969X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112932714","display_name":"Yishuang Li","orcid":"https://orcid.org/0009-0003-3466-0701","observed_orcids":["https://orcid.org/0009-0003-3466-0701"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yishuang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692702","display_name":"Hukai Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hukai Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690","observed_orcids":["https://orcid.org/0000-0001-7380-8690"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Lin Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8876,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75877961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4304","last_page":"4308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9603999853134155,"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":0.9603999853134155,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03550000116229057,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.0013000000035390258,"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/text-to-speech","display_name":"text-to-speech","score":0.8539999723434448},{"id":"https://openalex.org/keywords/style-transfer","display_name":"style transfer","score":0.8700000047683716},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.796999990940094},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.5270000100135803}],"concepts":[{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.7557535171508789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6583211421966553},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6207525134086609},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5225490927696228},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44565534591674805},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3871120810508728},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0993262529373169},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08551999926567078},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0815851092338562},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2023-1151","doi":"https://doi.org/10.21437/interspeech.2023-1151","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1151","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2306.04301","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.04301","pdf_url":"https://arxiv.org/pdf/2306.04301","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2306.04301","doi":"https://doi.org/10.48550/arxiv.2306.04301","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.04301","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.04301","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.04301","pdf_url":"https://arxiv.org/pdf/2306.04301","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822757.pdf","grobid_xml":"https://content.openalex.org/works/W4385822757.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415135890","https://openalex.org/W2904459034","https://openalex.org/W3205631867","https://openalex.org/W4385822787","https://openalex.org/W4312254071","https://openalex.org/W4417291460","https://openalex.org/W4412945647","https://openalex.org/W4380714711","https://openalex.org/W4283662594","https://openalex.org/W4296069154"],"abstract_inverted_index":{"With":[0],"the":[1,10,73,77,100,118],"demand":[2],"for":[3],"autonomous":[4],"control":[5,12],"and":[6,13,21,40,54,64,76,98,121],"personalized":[7],"speech":[8],"generation,":[9],"style":[11,36,80,96,103,111],"transfer":[14,37],"in":[15],"Text-to-Speech":[16],"(TTS)":[17],"is":[18,89,134],"becoming":[19],"more":[20,22,135],"important.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,44,113],"propose":[28],"a":[29,46,62,65,83,107],"new":[30],"TTS":[31,47],"system":[32,48,67],"that":[33,49,131],"can":[34],"perform":[35],"with":[38],"interpretability":[39,124],"high":[41],"fidelity.":[42],"Firstly,":[43],"design":[45],"combines":[50],"variational":[51],"autoencoder":[52],"(VAE)":[53],"diffusion":[55,84],"refiner":[56],"to":[57,71,91,116],"get":[58],"refined":[59],"mel-spectrograms.":[60],"Specifically,":[61],"two-stage":[63],"one-stage":[66],"are":[68],"designed":[69,90],"respectively,":[70],"improve":[72,99,117],"audio":[74],"quality":[75,120],"performance":[78,101],"of":[79,86,102,110],"transfer.":[81,104],"Secondly,":[82],"bridge":[85],"quantized":[87],"VAE":[88],"efficiently":[92],"learn":[93],"complex":[94],"discrete":[95],"representations":[97],"To":[105],"have":[106,122],"better":[108],"ability":[109],"transfer,":[112],"introduce":[114],"ControlVAE":[115],"reconstruction":[119],"good":[123],"simultaneously.":[125],"Experiments":[126],"on":[127],"LibriTTS":[128],"dataset":[129],"demonstrate":[130],"our":[132],"method":[133],"effective":[136],"than":[137],"baseline":[138],"models.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2023-08-15T00:00:00"}