{"id":"https://openalex.org/W3160289600","doi":"https://doi.org/10.1109/icassp39728.2021.9414870","title":"Fcl-Taco2: Towards Fast, Controllable and Lightweight Text-to-Speech Synthesis","display_name":"Fcl-Taco2: Towards Fast, Controllable and Lightweight Text-to-Speech Synthesis","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160289600","doi":"https://doi.org/10.1109/icassp39728.2021.9414870","mag":"3160289600"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414870","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":"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/A5068726270","display_name":"Disong Wang","orcid":"https://orcid.org/0000-0001-8481-6880"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Disong Wang","raw_affiliation_strings":["The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044738402","display_name":"Liqun Deng","orcid":"https://orcid.org/0009-0006-7242-0794"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Liqun Deng","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596907","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0002-3588-4702"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046186949","display_name":"Nianzu Zheng","orcid":"https://orcid.org/0000-0001-6300-9684"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Nianzu Zheng","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373698","display_name":"Xiao Dong Chen","orcid":"https://orcid.org/0000-0002-0150-0491"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab","Huawei Noah's Ark Lab"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5068726270"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.2237,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8295007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5714","last_page":"5718"},"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":0.9962000250816345,"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":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.7404524683952332},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6839868426322937},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6076809167861938},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5481449365615845},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.523697018623352},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4686426818370819},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.45003387331962585},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4429200291633606},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4331579804420471},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.42667266726493835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35501372814178467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404524683952332},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6839868426322937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6076809167861938},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5481449365615845},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.523697018623352},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4686426818370819},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45003387331962585},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4429200291633606},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4331579804420471},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.42667266726493835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35501372814178467},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414870","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W2043003570","https://openalex.org/W2064675550","https://openalex.org/W2163605009","https://openalex.org/W2739879705","https://openalex.org/W2747874407","https://openalex.org/W2903739847","https://openalex.org/W2945613576","https://openalex.org/W2946200149","https://openalex.org/W2962780374","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964301388","https://openalex.org/W2964309167","https://openalex.org/W2970730223","https://openalex.org/W2972519044","https://openalex.org/W2998655561","https://openalex.org/W2999160446","https://openalex.org/W3015282541","https://openalex.org/W3015338123","https://openalex.org/W3016136182","https://openalex.org/W3025013833","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3034949308","https://openalex.org/W3047068494","https://openalex.org/W3048173247","https://openalex.org/W3095883095","https://openalex.org/W3097144763","https://openalex.org/W3105966348","https://openalex.org/W3130016944","https://openalex.org/W3150572638","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6684191040","https://openalex.org/W6749489859","https://openalex.org/W6760712927","https://openalex.org/W6763832098","https://openalex.org/W6768086466","https://openalex.org/W6769767169","https://openalex.org/W6772321671","https://openalex.org/W6773094808","https://openalex.org/W6774506286","https://openalex.org/W6777340644","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6782348501","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294","https://openalex.org/W2368700418"],"abstract_inverted_index":{"Sequence-to-sequence":[0],"(seq2seq)":[1],"learning":[2],"has":[3,135],"greatly":[4],"improved":[5],"text-to-speech":[6],"(TTS)":[7],"synthesis":[8],"performance,":[9],"but":[10],"effective":[11],"implementation":[12],"on":[13,53,70,109,147,157],"resource-restricted":[14],"devices":[15,159],"remains":[16],"challenging":[17],"as":[18],"seq2seq":[19],"models":[20],"are":[21,177],"usually":[22],"computationally":[23],"expensive":[24],"and":[25,33,47,78,112,142,151,174],"memory":[26],"intensive.":[27],"To":[28],"achieve":[29,166],"fast":[30],"inference":[31,76,145],"speed":[32,77],"small":[34,99,119],"model":[35,51,96,164],"size":[36],"while":[37,133],"maintain":[38],"high-quality":[39],"speech,":[40],"we":[41],"propose":[42],"FCL-taco2,":[43],"a":[44,57,92,136],"Fast,":[45],"Controllable":[46],"Lightweight":[48],"(FCL)":[49],"TTS":[50],"based":[52,65],"Tacotron2.":[54,83],"FCL-taco2":[55,95,122],"adopts":[56],"novel":[58],"semi-autoregressive":[59],"(SAR)":[60],"mode":[61],"for":[62,149],"phoneme":[63],"level":[64],"parallel":[66],"mel-spectrograms":[67],"generation":[68],"conditioned":[69],"prosody":[71,80],"features,":[72],"leading":[73],"to":[74,90,97],"faster":[75,144,167],"higher":[79],"controllability":[81],"than":[82,168],"Besides,":[84,155],"knowledge":[85],"distillation":[86],"(KD)":[87],"is":[88],"leveraged":[89],"compress":[91],"relatively":[93],"large":[94],"its":[98],"version":[100,120],"with":[101,126,140],"minor":[102],"loss":[103],"of":[104,121,130],"speech":[105,131,170],"quality.":[106],"Experimental":[107],"results":[108],"English":[110],"(EN)":[111],"Chinese":[113],"(CN)":[114],"datasets":[115],"show":[116],"that":[117,161],"the":[118,162],"achieves":[123],"comparable":[124],"performance":[125],"Tacotron2":[127],"in":[128],"terms":[129],"quality,":[132],"it":[134],"4.8\u00d7":[137],"smaller":[138],"footprint":[139],"17.7\u00d7":[141],"18.5\u00d7":[143],"speeds":[146],"average":[148],"EN":[150],"CN":[152],"experiments":[153],"respectively.":[154],"execution":[156],"mobile":[158],"shows":[160],"proposed":[163],"can":[165],"real-time":[169],"synthesis.":[171],"Our":[172],"code":[173],"audio":[175],"samples":[176],"released":[178],"<sup":[179],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[180],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[181],".":[182]},"counts_by_year":[{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}