{"id":"https://openalex.org/W4410770313","doi":"https://doi.org/10.1109/icasspw65056.2025.11011026","title":"StableTTS: Towards Efficient Denoising Acoustic Decoder for Text to Speech Synthesis with Consistency Flow Matching","display_name":"StableTTS: Towards Efficient Denoising Acoustic Decoder for Text to Speech Synthesis with Consistency Flow Matching","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410770313","doi":"https://doi.org/10.1109/icasspw65056.2025.11011026"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5100370053","display_name":"Zhiyong Chen","orcid":"https://orcid.org/0000-0002-2033-4249"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Chen","raw_affiliation_strings":["Shanghai University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai,China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015889784","display_name":"Xinnuo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinnuo Li","raw_affiliation_strings":["New York University,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University,New York,USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048012502","display_name":"Shuhang Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhang Wu","raw_affiliation_strings":["Shanghai University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai,China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101561407","display_name":"Yang Zhi","orcid":"https://orcid.org/0000-0002-9768-2356"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Yang","raw_affiliation_strings":["Shanghai University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai,China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025619660","display_name":"Zhilong Ai","orcid":"https://orcid.org/0000-0002-5264-8875"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqi Ai","raw_affiliation_strings":["Shanghai University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai,China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084521046","display_name":"Shugong Xu","orcid":"https://orcid.org/0000-0003-1905-6269"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shugong Xu","raw_affiliation_strings":["Shanghai University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University,Shanghai,China","institution_ids":["https://openalex.org/I113940042"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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":0.992900013923645,"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":0.9889000058174133,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.6635088324546814},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.661491870880127},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6282444000244141},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6231338977813721},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5649921894073486},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.4123385548591614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27227941155433655},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12427020072937012},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.053993403911590576}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6635088324546814},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.661491870880127},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6282444000244141},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6231338977813721},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5649921894073486},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4123385548591614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27227941155433655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12427020072937012},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.053993403911590576},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011026","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011026","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1603736412","https://openalex.org/W1972035260","https://openalex.org/W4304185162","https://openalex.org/W2061685118","https://openalex.org/W3006282800","https://openalex.org/W2462100143","https://openalex.org/W1770503332","https://openalex.org/W3125207769","https://openalex.org/W4301594054","https://openalex.org/W2577825108"],"abstract_inverted_index":{"Current":[0],"state-of-the-art":[1],"text-to-speech":[2],"(TTS)":[3],"systems":[4,94],"predominantly":[5],"utilize":[6],"denoising-based":[7,55,107],"acoustic":[8,56],"decoders":[9,57],"with":[10,15,65,78,84],"language":[11],"models":[12],"(LLMs)":[13],"or":[14,61],"non-autoregressive":[16],"front-ends,":[17],"known":[18],"for":[19],"their":[20],"superior":[21],"performance":[22,53],"in":[23,58,69,88],"generating":[24],"high-fidelity":[25],"spectrum.":[26],"In":[27],"this":[28],"study,":[29],"we":[30,82],"introduce":[31],"an":[32,97],"efficient":[33,98],"TTS":[34,60,93,100],"system":[35],"that":[36],"incorporates":[37],"Consistency":[38],"Flow":[39],"Matching":[40],"denoising":[41,80],"training.":[42],"This":[43],"training":[44,49,71],"approach":[45],"significantly":[46],"enhances":[47],"the":[48,70,85,89,110],"efficiency":[50,111],"and":[51,95],"operational":[52],"of":[54,91,112],"existing":[59],"voice":[62],"conversion":[63],"systems,":[64],"no":[66],"additional":[67],"cost":[68],"process\u2014a":[72],"free":[73],"lunch.":[74],"To":[75],"efficiently":[76],"compare":[77],"other":[79],"strategies,":[81],"align":[83],"latest":[86],"advancements":[87],"implementation":[90],"non-autoregressive-based":[92],"build":[96],"DiT-based":[99],"architecture.":[101],"Our":[102],"comprehensive":[103],"evaluations":[104],"against":[105],"various":[106],"methods":[108],"affirm":[109],"our":[113],"proposed":[114],"system<sup":[115],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[116],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[117]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}