{"id":"https://openalex.org/W4415536424","doi":"https://doi.org/10.1145/3746027.3755494","title":"FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching","display_name":"FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536424","doi":"https://doi.org/10.1145/3746027.3755494"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755494","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5115597140","display_name":"Hui Wang","orcid":"https://orcid.org/0009-0003-8057-4644"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hui Wang","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0003-8057-4644","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101635405","display_name":"Shujie Liu","orcid":"https://orcid.org/0009-0008-2599-6752"},"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"]},{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Shujie Liu","raw_affiliation_strings":["Microsoft Corporation, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0008-2599-6752","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Hong Kong, China","institution_ids":["https://openalex.org/I4210105678","https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089153961","display_name":"Lingwei Meng","orcid":null},"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":"Lingwei Meng","raw_affiliation_strings":["Microsoft Corporation, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1028-6017","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"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":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0002-1089-9748","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596565","display_name":"Yifan Yang","orcid":"https://orcid.org/0009-0003-0588-1812"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Microsoft Corporation, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-0588-1812","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052465353","display_name":"Shiwan Zhao","orcid":"https://orcid.org/0000-0001-5068-025X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwan Zhao","raw_affiliation_strings":["College of Computer Science, Nankai University, Tanjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5068-025X","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tanjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066697166","display_name":"Haiyang Sun","orcid":"https://orcid.org/0009-0004-3485-3869"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"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":"Haiyang Sun","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China","Microsoft Corporation, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3485-3869","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yanqing Liu","orcid":"https://orcid.org/0000-0002-4150-0680"},"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":"Yanqing Liu","raw_affiliation_strings":["Microsoft Corporation, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4150-0680","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035524175","display_name":"Haoqin Sun","orcid":"https://orcid.org/0000-0002-8554-8969"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"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":"Haoqin Sun","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China","Microsoft Corporation, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8554-8969","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113361562","display_name":"Jiaming Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhou","raw_affiliation_strings":["College of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0002-4819-4572","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100756584","display_name":"Yan Lu","orcid":"https://orcid.org/0000-0001-5383-6424"},"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":"Yan Lu","raw_affiliation_strings":["Microsoft Corporation, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5383-6424","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010808374","display_name":"Yong Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["College of Computer Science, Nankai University, Tian Jin, China"],"raw_orcid":"https://orcid.org/0009-0000-2748-3020","affiliations":[{"raw_affiliation_string":"College of Computer Science, Nankai University, Tian Jin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5115597140"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1557648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10229","last_page":"10238"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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":0.9977999925613403,"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/autoregressive-model","display_name":"Autoregressive model","score":0.885200023651123},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5723999738693237},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5083000063896179},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4991999864578247},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4564000070095062},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.39980000257492065},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.38019999861717224},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.36320000886917114}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.885200023651123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495999932289124},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5723999738693237},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5110999941825867},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43290001153945923},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.38019999861717224},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3612000048160553},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.36000001430511475},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3562999963760376},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755494","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":8,"referenced_works":["https://openalex.org/W3097777922","https://openalex.org/W3202278141","https://openalex.org/W4226332109","https://openalex.org/W4381786045","https://openalex.org/W4385823334","https://openalex.org/W4402112248","https://openalex.org/W4406417959","https://openalex.org/W4408592567"],"related_works":[],"abstract_inverted_index":{"To":[0],"advance":[1],"continuous":[2],"token":[3],"modeling":[4,17],"and":[5,30,65],"temporal-coherence":[6],"enforcement,":[7],"we":[8],"propose":[9],"FELLE,":[10],"an":[11],"autoregressive":[12,25,98],"model":[13],"that":[14],"integrates":[15],"language":[16,28,85],"with":[18],"token-wise":[19],"flow":[20,35,54],"matching.":[21],"By":[22],"leveraging":[23],"the":[24,31,49,60,84,91],"nature":[26],"of":[27,34,93],"models":[29],"generative":[32],"efficacy":[33],"matching,":[36],"FELLE":[37,47,72],"effectively":[38],"predicts":[39],"continuous-valued":[40,45,79],"tokens":[41,80],"(mel-spectrograms).":[42],"For":[43],"each":[44],"token,":[46],"modifies":[48],"general":[50],"prior":[51],"distribution":[52],"in":[53,97,105,111],"matching":[55],"by":[56],"incorporating":[57,94],"information":[58],"from":[59],"previous":[61],"step,":[62],"improving":[63],"coherence":[64],"stability.":[66],"Furthermore,":[67],"to":[68,102],"enhance":[69],"synthesis":[70],"quality,":[71,108],"introduces":[73],"a":[74],"coarse-to-fine":[75],"flow-matching":[76,95],"mechanism,":[77],"generating":[78],"hierarchically,":[81],"conditioned":[82],"on":[83],"model's":[86],"output.":[87],"Experimental":[88],"results":[89],"demonstrate":[90],"potential":[92],"techniques":[96],"mel-spectrogram":[99],"modeling,":[100],"leading":[101],"significant":[103],"improvements":[104],"TTS":[106],"generation":[107],"as":[109],"shown":[110],"https://aka.ms/felle.":[112]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}