{"id":"https://openalex.org/W3015607139","doi":"https://doi.org/10.1109/icassp40776.2020.9053812","title":"Extracting Unit Embeddings Using Sequence-To-Sequence Acoustic Models for Unit Selection Speech Synthesis","display_name":"Extracting Unit Embeddings Using Sequence-To-Sequence Acoustic Models for Unit Selection Speech Synthesis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015607139","doi":"https://doi.org/10.1109/icassp40776.2020.9053812","mag":"3015607139"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5084534688","display_name":"Zhou Xiao","orcid":"https://orcid.org/0000-0001-5263-365X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhou","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"7659","last_page":"7663"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9955000281333923,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9952999949455261,"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/concatenation","display_name":"Concatenation (mathematics)","score":0.8689334988594055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6491182446479797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6402368545532227},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.620498538017273},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6075754165649414},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5682087540626526},{"id":"https://openalex.org/keywords/unit-vector","display_name":"Unit vector","score":0.5355610251426697},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5217453241348267},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5169050693511963},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4471639394760132},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4317362904548645},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.42299407720565796},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4188935160636902},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.412089467048645},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3597950339317322},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2952025532722473},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22639605402946472},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22470608353614807},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.10532203316688538}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8689334988594055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6491182446479797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6402368545532227},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.620498538017273},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6075754165649414},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5682087540626526},{"id":"https://openalex.org/C84316537","wikidata":"https://www.wikidata.org/wiki/Q36255","display_name":"Unit vector","level":2,"score":0.5355610251426697},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5217453241348267},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5169050693511963},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4471639394760132},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4317362904548645},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.42299407720565796},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4188935160636902},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.412089467048645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3597950339317322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2952025532722473},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22639605402946472},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22470608353614807},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.10532203316688538},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":23,"referenced_works":["https://openalex.org/W67398698","https://openalex.org/W854541894","https://openalex.org/W1572730534","https://openalex.org/W2128160875","https://openalex.org/W2129142580","https://openalex.org/W2133564696","https://openalex.org/W2150658333","https://openalex.org/W2187089797","https://openalex.org/W2394761397","https://openalex.org/W2674088828","https://openalex.org/W2746788734","https://openalex.org/W2792191066","https://openalex.org/W2883746099","https://openalex.org/W2888976811","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W4395961086","https://openalex.org/W6602693416","https://openalex.org/W6623517193","https://openalex.org/W6679434410","https://openalex.org/W6711946264","https://openalex.org/W6865569971"],"related_works":["https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2899044948","https://openalex.org/W205537210","https://openalex.org/W2161566404"],"abstract_inverted_index":{"This":[0],"paper":[1,161],"presents":[2],"a":[3,16,47,62,150],"method":[4,157],"of":[5,33,65,106,137,166],"using":[6,149],"the":[7,21,31,34,42,66,71,92,103,117,125,156,164],"intermediate":[8],"representations":[9],"between":[10,79],"linguistic":[11],"and":[12,89,134,152],"acoustic":[13,135,154],"features":[14],"in":[15,41,159,171],"Tacotron":[17,35,130],"model":[18],"to":[19,55,85,90,115],"derive":[20,116],"cost":[22,94,119],"functions":[23],"for":[24,95],"unit":[25,40,49,54,63,87,96,104,126,147,167],"selection":[26,168],"speech":[27,169],"synthesis.":[28],"By":[29],"extracting":[30],"outputs":[32],"encoder,":[36],"each":[37,52,107],"phone-sized":[38],"candidate":[39],"corpus":[43],"is":[44,58,113],"represented":[45],"by":[46,69],"fixed-length":[48],"vector.":[50],"Similarly,":[51],"target":[53,93],"be":[56],"synthesized":[57],"also":[59],"converted":[60],"into":[61],"vector":[64,105],"same":[67],"dimension":[68],"encoding":[70],"input":[72],"phone":[73,108,138],"sequence.":[74],"The":[75],"normalized":[76],"Euclidean":[77],"distances":[78],"these":[80],"two":[81],"vectors":[82,127,148],"are":[83],"utilized":[84],"fulfill":[86],"pre-selection":[88],"calculate":[91],"selection.":[97],"Then,":[98],"another":[99],"DNN":[100,151],"which":[101,145],"predicts":[102],"from":[109,129],"its":[110],"preceding":[111],"ones":[112],"constructed":[114],"concatenation":[118],"function.":[120],"Experimental":[121],"results":[122],"demonstrate":[123],"that":[124],"extracted":[128],"contain":[131],"both":[132],"duration":[133],"information":[136],"units.":[139],"Comparing":[140],"with":[141],"our":[142,172],"previous":[143],"work,":[144],"learned":[146],"only":[153],"features,":[155],"proposed":[158],"this":[160],"further":[162],"improves":[163],"naturalness":[165],"synthesis":[170],"experiments.":[173]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
