{"id":"https://openalex.org/W4408347240","doi":"https://doi.org/10.1109/icassp49660.2025.10889258","title":"SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow","display_name":"SlimSpeech: Lightweight and Efficient Text-to-Speech with Slim Rectified Flow","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347240","doi":"https://doi.org/10.1109/icassp49660.2025.10889258"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5113251188","display_name":"Kaidi Wang","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":"Kaidi Wang","raw_affiliation_strings":["Xiamen University,School of Informatics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","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 Electronic Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111310820","display_name":"Shenghui Lu","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":"Shenghui Lu","raw_affiliation_strings":["Xiamen University,School of Informatics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109475001","display_name":"J. Yao","orcid":"https://orcid.org/0009-0007-5433-5868"},"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":"Jianglong Yao","raw_affiliation_strings":["Xiamen University,School of Informatics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103050255","display_name":"Lin Li","orcid":"https://orcid.org/0000-0002-5021-2648"},"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":"Lin Li","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112311097","display_name":"Qingyang Hong","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":"Qingyang Hong","raw_affiliation_strings":["Xiamen University,School of Informatics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/T12031","display_name":"Speech and dialogue systems","score":0.9918000102043152,"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/T12031","display_name":"Speech and dialogue systems","score":0.9918000102043152,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9822999835014343,"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":0.9757999777793884,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7197742462158203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6005547046661377},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.43809956312179565},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09067925810813904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7197742462158203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6005547046661377},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.43809956312179565},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09067925810813904},{"id":"https://openalex.org/C57879066","wikidata":"https://www.wikidata.org/wiki/Q41217","display_name":"Mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2531409750","https://openalex.org/W2903739847","https://openalex.org/W2964243274","https://openalex.org/W3162046328","https://openalex.org/W3198213150","https://openalex.org/W4206662443","https://openalex.org/W4252812408","https://openalex.org/W4304099317","https://openalex.org/W4372260261","https://openalex.org/W4385822757","https://openalex.org/W4387968164","https://openalex.org/W4392904491","https://openalex.org/W4392931276","https://openalex.org/W4392931781","https://openalex.org/W4402111756","https://openalex.org/W4402977416","https://openalex.org/W6739901393","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6795288823","https://openalex.org/W6810926057","https://openalex.org/W6811291704","https://openalex.org/W6843731886","https://openalex.org/W6846539466","https://openalex.org/W6849109464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Recently,":[0],"flow":[1,50],"matching":[2],"based":[3,34],"speech":[4,13,31,44],"synthesis":[5,32,45],"has":[6],"significantly":[7,103],"enhanced":[8],"the":[9,16,42,48,66,82,92],"quality":[10],"of":[11,18],"synthesized":[12],"while":[14,85],"reducing":[15],"number":[17],"inference":[19],"steps.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24,69],"introduce":[25],"SlimSpeech,":[26],"a":[27,61,72,76],"lightweight":[28],"and":[29,58],"efficient":[30],"system":[33],"on":[35],"rectified":[36,49],"flow.":[37],"We":[38],"have":[39],"built":[40],"upon":[41],"existing":[43],"method":[46],"utilizing":[47,86],"model,":[51,84],"modifying":[52],"its":[53],"structure":[54],"to":[55,89,110],"reduce":[56],"parameters":[57],"serve":[59],"as":[60],"teacher":[62],"model.":[63],"By":[64],"refining":[65],"reflow":[67],"operation,":[68],"directly":[70],"derive":[71],"smaller":[73],"model":[74,93,105],"with":[75,102],"more":[77],"straight":[78],"sampling":[79],"trajectory":[80],"from":[81],"larger":[83,111],"distillation":[87],"techniques":[88],"further":[90],"enhance":[91],"performance.":[94],"Experimental":[95],"results":[96],"demonstrate":[97],"that":[98],"our":[99],"proposed":[100],"method,":[101],"reduced":[104],"parameters,":[106],"achieves":[107],"comparable":[108],"performance":[109],"models":[112],"through":[113],"one-step":[114],"sampling.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}