{"id":"https://openalex.org/W4392931781","doi":"https://doi.org/10.1109/icassp48485.2024.10447822","title":"Reflow-TTS: A Rectified Flow Model for High-Fidelity Text-to-Speech","display_name":"Reflow-TTS: A Rectified Flow Model for High-Fidelity Text-to-Speech","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931781","doi":"https://doi.org/10.1109/icassp48485.2024.10447822"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5111310824","display_name":"Wenhao Guan","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Guan","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066310925","display_name":"Qi Su","orcid":"https://orcid.org/0000-0002-4769-2812"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Su","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010106071","display_name":"Haodong Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Zhou","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109643500","display_name":"Shiyu Miao","orcid":"https://orcid.org/0009-0006-1588-4760"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Miao","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059413261","display_name":"Xingjia Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingjia Xie","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115604806","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0980-6716"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10501","last_page":"10505"},"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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-synthesis","display_name":"Speech synthesis","score":0.7153010368347168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6913123726844788},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6011902689933777},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.509652853012085},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4916442036628723},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.46243155002593994},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.42619913816452026},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34444430470466614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33991044759750366},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09799641370773315},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09598410129547119},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08329516649246216}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7153010368347168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913123726844788},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6011902689933777},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.509652853012085},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4916442036628723},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.46243155002593994},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42619913816452026},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34444430470466614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33991044759750366},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09799641370773315},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09598410129547119},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08329516649246216},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2299475589","display_name":null,"funder_award_id":"62001405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3698338998","display_name":null,"funder_award_id":"61876160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2963755523","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3097538987","https://openalex.org/W3158762648","https://openalex.org/W3198213150","https://openalex.org/W4226063663","https://openalex.org/W4229944339","https://openalex.org/W4297676498","https://openalex.org/W4304099317","https://openalex.org/W4313447020","https://openalex.org/W4382603054","https://openalex.org/W4385245566","https://openalex.org/W4385822757","https://openalex.org/W4387968164","https://openalex.org/W6631190155","https://openalex.org/W6752307458","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6795261426","https://openalex.org/W6810926057","https://openalex.org/W6843731886","https://openalex.org/W6846539466","https://openalex.org/W6848482659","https://openalex.org/W6849109464","https://openalex.org/W6853888607","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W4224231624","https://openalex.org/W2332512904","https://openalex.org/W2319626700"],"abstract_inverted_index":{"The":[0],"diffusion":[1,135],"models":[2,12],"including":[3],"Denoising":[4],"Diffusion":[5],"Probabilistic":[6],"Models":[7],"(DDPM)":[8],"and":[9,109],"score-based":[10],"generative":[11],"have":[13],"demonstrated":[14],"excellent":[15],"performance":[16,131,147],"in":[17,33,48],"speech":[18,64,102],"synthesis":[19,65,103],"tasks.":[20],"However,":[21],"its":[22,45],"effectiveness":[23],"comes":[24],"at":[25],"the":[26,84,111,129,139],"cost":[27],"of":[28],"numerous":[29],"sampling":[30,35,107,144],"steps,":[31],"resulting":[32],"prolonged":[34],"time":[36],"required":[37],"to":[38,83],"synthesize":[39],"high-quality":[40,101],"speech.":[41],"This":[42],"drawback":[43],"hinders":[44],"practical":[46],"applicability":[47],"real-world":[49],"scenarios.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"introduce":[55],"ReFlow-TTS,":[56],"a":[57,105,115],"novel":[58],"rectified":[59],"flow":[60],"based":[61,136],"method":[62,127],"for":[63,113],"with":[66,104,133,141,149],"high-fidelity.":[67],"Specifically,":[68],"our":[69,97,125],"ReFlow-TTS":[70,126,140],"is":[71],"simply":[72],"an":[73],"Ordinary":[74],"Differential":[75],"Equation":[76],"(ODE)":[77],"model":[78],"that":[79,124],"transports":[80],"Gaussian":[81],"distribution":[82,87],"ground-truth":[85],"Mel-spectrogram":[86],"by":[88],"straight":[89],"line":[90],"paths":[91],"as":[92,94],"much":[93],"possible.":[95],"Furthermore,":[96],"proposed":[98],"approach":[99],"enables":[100],"single":[106],"step":[108,143],"eliminates":[110],"need":[112],"training":[114],"teacher":[116],"model.":[117],"Our":[118],"experiments":[119],"on":[120],"LJSpeech":[121],"Dataset":[122],"show":[123],"achieves":[128,145],"best":[130],"compared":[132,148],"other":[134],"models.":[137,153],"And":[138],"one":[142],"competitive":[146],"existing":[150],"one-step":[151],"TTS":[152]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}