{"id":"https://openalex.org/W3151292345","doi":"https://doi.org/10.1109/slt48900.2021.9383562","title":"Lightspeech: Lightweight Non-Autoregressive Multi-Speaker Text-To-Speech","display_name":"Lightspeech: Lightweight Non-Autoregressive Multi-Speaker Text-To-Speech","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3151292345","doi":"https://doi.org/10.1109/slt48900.2021.9383562","mag":"3151292345"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5100448180","display_name":"Song Li","orcid":"https://orcid.org/0000-0001-5611-1517"},"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/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"499","last_page":"506"},"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":0.9987999796867371,"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":0.9979000091552734,"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/autoregressive-model","display_name":"Autoregressive model","score":0.8201361894607544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8049581050872803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.736243724822998},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7341103553771973},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6391973495483398},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5337684154510498},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5190147161483765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3800760805606842},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3299548625946045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06857830286026001}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8201361894607544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8049581050872803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.736243724822998},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7341103553771973},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6391973495483398},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5337684154510498},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5190147161483765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3800760805606842},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3299548625946045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06857830286026001},{"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/slt48900.2021.9383562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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":49,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1990505856","https://openalex.org/W2066195249","https://openalex.org/W2098372067","https://openalex.org/W2102003408","https://openalex.org/W2107860279","https://openalex.org/W2117671523","https://openalex.org/W2127141656","https://openalex.org/W2150791533","https://openalex.org/W2154920538","https://openalex.org/W2531409750","https://openalex.org/W2591927543","https://openalex.org/W2619368999","https://openalex.org/W2627092829","https://openalex.org/W2766812927","https://openalex.org/W2788357188","https://openalex.org/W2808706139","https://openalex.org/W2886769154","https://openalex.org/W2887511658","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/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2971753973","https://openalex.org/W2972359262","https://openalex.org/W2972382840","https://openalex.org/W3015338123","https://openalex.org/W3015645837","https://openalex.org/W3015826515","https://openalex.org/W4231812008","https://openalex.org/W6728184133","https://openalex.org/W6734815144","https://openalex.org/W6739366949","https://openalex.org/W6745697700","https://openalex.org/W6748588790","https://openalex.org/W6752888775","https://openalex.org/W6754925833","https://openalex.org/W6757585730","https://openalex.org/W6763832098","https://openalex.org/W6765987481","https://openalex.org/W6813539834"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"With":[0,67],"the":[1,53,63,68,80,101],"development":[2],"of":[3,20,65],"deep":[4],"learning,":[5],"end-to-end":[6],"neural":[7,56],"text-to-speech":[8],"systems":[9,22],"have":[10],"achieved":[11],"significant":[12],"improvements":[13],"on":[14,79,98],"high-quality":[15],"speech":[16,46,74],"synthesis.":[17],"However,":[18],"most":[19],"these":[21],"are":[23,106],"attention-based":[24],"autoregressive":[25],"models,":[26],"resulting":[27],"in":[28],"slow":[29],"synthesis":[30,47,60,75],"speed":[31],"and":[32,61,100,104,110],"large":[33],"model":[34,91,102],"parameters.":[35,66],"In":[36],"this":[37],"paper,":[38],"we":[39],"propose":[40],"a":[41,93],"new":[42],"lightweight":[43,54],"non-autoregressive":[44],"multi-speaker":[45,73],"system,":[48],"named":[49],"LightSpeech,":[50],"which":[51],"utilizes":[52],"feedforward":[55],"networks":[57],"to":[58],"accelerate":[59],"reduce":[62],"amount":[64],"speaker":[69],"embedding,":[70],"LightSpeech":[71,90],"achieves":[72,92],"extremely":[76],"quickly.":[77],"Experiments":[78],"LibriTTS":[81],"dataset":[82],"show":[83],"that,":[84],"compared":[85],"with":[86],"FastSpeech,":[87],"our":[88],"smallest":[89],"9.27x":[94],"Mel-spectrogram":[95],"generation":[96],"acceleration":[97],"CPU,":[99],"size":[103],"parameters":[105],"compressed":[107],"by":[108],"37.06x":[109],"37.36x,":[111],"respectively.":[112]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}