{"id":"https://openalex.org/W3162046328","doi":"https://doi.org/10.1109/icassp39728.2021.9414400","title":"Light-TTS: Lightweight Multi-Speaker Multi-Lingual Text-to-Speech","display_name":"Light-TTS: Lightweight Multi-Speaker Multi-Lingual Text-to-Speech","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162046328","doi":"https://doi.org/10.1109/icassp39728.2021.9414400","mag":"3162046328"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5100448204","display_name":"Song Li","orcid":"https://orcid.org/0000-0002-6797-143X"},"institutions":[{"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":"Song Li","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"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/A5066579310","display_name":"Beibei Ouyang","orcid":null},"institutions":[{"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":"Beibei Ouyang","raw_affiliation_strings":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"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/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":["School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"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":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"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":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8383","last_page":"8387"},"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":0.9991999864578247,"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":0.9973999857902527,"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":0.8070690631866455},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7400045394897461},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7091882824897766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6740418672561646},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5721546411514282},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49191808700561523},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4462161660194397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38970643281936646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8070690631866455},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7400045394897461},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7091882824897766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6740418672561646},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5721546411514282},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49191808700561523},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4462161660194397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38970643281936646},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.550000011920929}],"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":31,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2091425152","https://openalex.org/W2098372067","https://openalex.org/W2767052532","https://openalex.org/W2788357188","https://openalex.org/W2808706139","https://openalex.org/W2890964092","https://openalex.org/W2892140764","https://openalex.org/W2908336025","https://openalex.org/W2945613576","https://openalex.org/W2946200149","https://openalex.org/W2952809536","https://openalex.org/W2963192573","https://openalex.org/W2963432880","https://openalex.org/W2963609956","https://openalex.org/W2963736842","https://openalex.org/W2964110616","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2971753973","https://openalex.org/W2972382840","https://openalex.org/W3015338123","https://openalex.org/W3015826515","https://openalex.org/W6631362777","https://openalex.org/W6748588790","https://openalex.org/W6752888775","https://openalex.org/W6754925833","https://openalex.org/W6757585730","https://openalex.org/W6762774924","https://openalex.org/W6763832098","https://openalex.org/W6767453231"],"related_works":["https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W4253660971","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469"],"abstract_inverted_index":{"With":[0],"the":[1,51,54,77,100,120],"development":[2],"of":[3,21,53,83,103],"deep":[4],"learning,":[5],"end-to-end":[6],"neural":[7,104],"text-to-speech":[8],"(TTS)":[9],"systems":[10,23],"have":[11],"achieved":[12],"significant":[13],"improvements":[14],"in":[15,29,40,86],"high-quality":[16],"speech":[17,39,55,68,82],"synthesis.":[18],"However,":[19],"most":[20],"these":[22],"are":[24,122],"attention-based":[25],"autoregressive":[26],"models,":[27,48],"resulting":[28],"slow":[30],"synthesis":[31,56,69],"speed":[32],"and":[33,107,119],"large":[34],"model":[35],"parameters.":[36],"In":[37,58],"addition,":[38],"different":[41,47],"languages":[42],"is":[43],"usually":[44],"synthesized":[45],"using":[46,91],"which":[49,73],"increases":[50],"complexity":[52],"systems.":[57],"this":[59],"paper,":[60],"we":[61],"propose":[62],"a":[63,87,112],"new":[64],"lightweight":[65],"multi-speaker":[66],"multi-lingual":[67],"system,":[70],"named":[71],"LightTTS,":[72],"can":[74],"quickly":[75],"synthesize":[76],"Chinese,":[78],"English":[79],"or":[80],"code-switch":[81],"multiple":[84],"speakers":[85],"non-autoregressive":[88],"generation":[89,115],"manner":[90],"only":[92],"one":[93],"model.":[94],"Moreover,":[95],"compared":[96],"to":[97],"FastSpeech":[98],"with":[99],"same":[101],"number":[102],"network":[105],"layers":[106],"nodes,":[108],"our":[109],"LightTTS":[110],"achieves":[111],"2.50x":[113],"Mel-spectrum":[114],"acceleration":[116],"on":[117],"CPU,":[118],"parameters":[121],"compressed":[123],"by":[124],"12.83x.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}