{"id":"https://openalex.org/W3195077602","doi":"https://doi.org/10.21437/ssw.2021-35","title":"FeatherTTS: Robust and Efficient attention based Neural TTS","display_name":"FeatherTTS: Robust and Efficient attention based Neural TTS","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3195077602","doi":"https://doi.org/10.21437/ssw.2021-35","mag":"3195077602"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-35","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-35","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","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/A5018710096","display_name":"Qiao Tian","orcid":"https://orcid.org/0000-0001-8177-7724"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiao Tian","raw_affiliation_strings":["Tencent,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101620277","display_name":"Chao Liu","orcid":"https://orcid.org/0000-0003-3992-0229"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Liu","raw_affiliation_strings":["Harbin Institute of Technology(Shenzhen),"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology(Shenzhen),","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048848376","display_name":"Zewang Zhang","orcid":"https://orcid.org/0009-0001-3620-8706"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zewang Zhang","raw_affiliation_strings":["Tencent,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Lu","raw_affiliation_strings":["Tencent,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101593418","display_name":"Ling-Hui Chen","orcid":"https://orcid.org/0009-0009-4247-4128"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linghui Chen","raw_affiliation_strings":["Tencent,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101632070","display_name":"Bin Wei","orcid":"https://orcid.org/0000-0003-4926-873X"},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bin Wei","raw_affiliation_strings":["Intel Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002488866","display_name":"Pujiang He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pujiang He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100449791","display_name":"Shan Liu","orcid":"https://orcid.org/0000-0002-1442-1207"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Shan Liu","raw_affiliation_strings":["Intel Corporation","Tencent,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]},{"raw_affiliation_string":"Tencent,","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048848376"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.5861,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68364799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"200","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9990000128746033,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9980999827384949,"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":0.698120653629303},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4461532235145569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4336540102958679},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3218720555305481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698120653629303},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4461532235145569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4336540102958679},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3218720555305481}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/ssw.2021-35","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-35","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1810943226","https://openalex.org/W1902237438","https://openalex.org/W2120847449","https://openalex.org/W2133564696","https://openalex.org/W2519091744","https://openalex.org/W2605141709","https://openalex.org/W2767785892","https://openalex.org/W2886769154","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2947723875","https://openalex.org/W2948238043","https://openalex.org/W2963091184","https://openalex.org/W2963609956","https://openalex.org/W2963827314","https://openalex.org/W2964243274","https://openalex.org/W3015922793","https://openalex.org/W3024747869","https://openalex.org/W3096702751","https://openalex.org/W4297689207"],"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":{"Attention":[0],"based":[1],"neural":[2,55],"TTS":[3,56],"is":[4,20],"elegant":[5],"speech":[6,103],"synthesis":[7],"pipeline":[8],"and":[9,52,70,126],"has":[10],"shown":[11],"a":[12,50,60,155],"powerful":[13],"ability":[14],"to":[15,25,40,100],"generate":[16],"natural":[17],"speech.However,":[18],"it":[19,33],"still":[21],"not":[22,112],"robust":[23,51],"enough":[24],"meet":[26],"the":[27,41,71,81,97,116,128,145],"stability":[28],"requirements":[29],"for":[30],"industrial":[31],"products.Besides,":[32],"suffers":[34],"from":[35],"slow":[36],"inference":[37],"speed":[38,101],"owning":[39],"autoregressive":[42,98],"generation":[43,139],"process.In":[44],"this":[45,77],"work,":[46],"we":[47,58,79,92],"propose":[48,59],"FeatherTTS,":[49],"efficient":[53],"attention-based":[54],"system.Firstly,":[57],"novel":[61],"Gaussian":[62,68],"attention":[63,69],"which":[64],"utilizes":[65],"interpretability":[66],"of":[67,118,130],"strict":[72],"monotonic":[73],"property":[74],"in":[75,122],"TTS.By":[76],"method,":[78],"replace":[80],"commonly":[82],"used":[83],"stop":[84,90],"token":[85],"prediction":[86],"architecture":[87],"with":[88],"attentive":[89],"prediction.Secondly,":[91],"apply":[93],"block":[94],"sparsity":[95],"on":[96,154],"decoder":[99],"up":[102,136],"synthesis.The":[104],"experimental":[105],"results":[106],"show":[107],"that":[108],"our":[109],"proposed":[110,146],"FeatherTTS":[111,147],"only":[113],"nearly":[114],"eliminates":[115],"problem":[117],"word":[119],"skipping,":[120],"repeating":[121],"particularly":[123],"hard":[124],"texts":[125],"keep":[127],"naturalness":[129],"generated":[131],"speech,":[132],"but":[133],"also":[134],"speeds":[135],"acoustic":[137],"feature":[138],"by":[140],"3.5":[141],"times":[142],"over":[143],"Tacotron.Overall,":[144],"can":[148],"be":[149],"35x":[150],"faster":[151],"than":[152],"real-time":[153],"single":[156],"CPU.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}