{"id":"https://openalex.org/W3160151995","doi":"https://doi.org/10.1109/icassp39728.2021.9413669","title":"The Thinkit System for Icassp2021 M2voc Challenge","display_name":"The Thinkit System for Icassp2021 M2voc Challenge","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160151995","doi":"https://doi.org/10.1109/icassp39728.2021.9413669","mag":"3160151995"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413669","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/A5085101543","display_name":"Zengqiang Shang","orcid":"https://orcid.org/0000-0002-9225-2138"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengqiang Shang","raw_affiliation_strings":["Key Laboratory of Speech Acoustics & Content Understanding, Institute of Acoustics, CAS, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics & Content Understanding, Institute of Acoustics, CAS, China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710295","display_name":"Haozhe Zhang","orcid":"https://orcid.org/0000-0002-0930-1980"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhe Zhang","raw_affiliation_strings":["Key Laboratory of Speech Acoustics & Content Understanding, Institute of Acoustics, CAS, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics & Content Understanding, Institute of Acoustics, CAS, China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368259","display_name":"Ziyi Chen","orcid":"https://orcid.org/0000-0001-6512-2824"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Chen","raw_affiliation_strings":["Key Laboratory of Speech Acoustics & Content Understanding, Institute of Acoustics, CAS, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics & Content Understanding, Institute of Acoustics, CAS, China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108929301","display_name":"Bolin Zhou","orcid":"https://orcid.org/0009-0002-6015-1743"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bolin Zhou","raw_affiliation_strings":["Key Laboratory of Speech Acoustics & Content Understanding, Institute of Acoustics, CAS, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics & Content Understanding, Institute of Acoustics, CAS, China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036446253","display_name":"Pengyuan Zhang","orcid":"https://orcid.org/0000-0001-6838-5160"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["Key Laboratory of Speech Acoustics & Content Understanding, Institute of Acoustics, CAS, China","University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics & Content Understanding, Institute of Acoustics, CAS, China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8396,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78217469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2017","issue":null,"first_page":"8593","last_page":"8597"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/T12031","display_name":"Speech and dialogue systems","score":0.9940999746322632,"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":0.7862119674682617},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6350047588348389},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.5535416007041931},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4825226962566376},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4808814823627472},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.47197872400283813},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4334980249404907},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.428041011095047},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4245578348636627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39053258299827576},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12691548466682434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862119674682617},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6350047588348389},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.5535416007041931},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4825226962566376},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4808814823627472},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.47197872400283813},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4334980249404907},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.428041011095047},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4245578348636627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39053258299827576},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12691548466682434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413669","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":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2746498480","https://openalex.org/W2747874407","https://openalex.org/W2788357188","https://openalex.org/W2892620417","https://openalex.org/W2937297115","https://openalex.org/W2946200149","https://openalex.org/W2949382160","https://openalex.org/W2954386831","https://openalex.org/W2963192573","https://openalex.org/W2963403868","https://openalex.org/W2963912924","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2970730223","https://openalex.org/W3015826515","https://openalex.org/W3016159759","https://openalex.org/W3024747869","https://openalex.org/W3025671734","https://openalex.org/W3048423403","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3095199334","https://openalex.org/W3095790275","https://openalex.org/W3095990227","https://openalex.org/W3098403858","https://openalex.org/W3162794600","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6748588790","https://openalex.org/W6755135894","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6777445600","https://openalex.org/W6783867762","https://openalex.org/W6785090365","https://openalex.org/W6792650190"],"related_works":["https://openalex.org/W2355553914","https://openalex.org/W149862513","https://openalex.org/W1974895211","https://openalex.org/W2347684782","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W4320472397"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,66,125],"introduce":[4],"the":[5,11,62,69,75,127,137,145,149],"low":[6,119],"resource":[7,120],"text-to-speech":[8],"system":[9],"from":[10,99,109],"ThinkIT":[12],"team":[13],"submitted":[14,82],"to":[15,95,106,118,135],"Multi-Speaker":[16],"Multi-Style":[17],"Voice":[18],"Cloning":[19],"Challenge":[20],"(M2VoC).":[21],"The":[22],"challenge":[23],"has":[24],"two":[25,45],"tasks:":[26],"few-shot":[27],"track1":[28],"provides":[29],"100":[30],"samples":[31,40],"for":[32],"each":[33],"person":[34],"and":[35,48,102,130],"one-shot":[36],"track2":[37],"offers":[38],"5":[39],"only.":[41,72],"Each":[42],"track":[43],"contains":[44],"sub-tracks":[46],"A":[47,71],"B.":[49],"Instead":[50],"of":[51,151],"sub-track":[52,54,70],"A,":[53],"B":[55],"can":[56],"use":[57],"extra":[58],"public":[59],"data":[60],"besides":[61],"released":[63],"data.":[64],"But":[65],"participate":[67],"in":[68],"We":[73],"choose":[74],"finetune":[76],"as":[77],"our":[78,152],"backbone":[79],"strategy.":[80],"Our":[81],"systems":[83],"include":[84],"BERT":[85],"based":[86,92,104],"prosody":[87],"boundary":[88],"prediction":[89],"module,":[90],"FastSpeech":[91],"acoustic":[93,97,110,114,128],"model":[94,129,139],"generate":[96,107],"features":[98],"text":[100],"input,":[101],"HIFIGAN":[103],"vocoder":[105],"waveform":[108],"features.":[111],"Among":[112],"them,":[113],"models":[115],"are":[116],"susceptible":[117],"speakers.":[121],"To":[122],"prevent":[123],"over-fitting,":[124],"modified":[126],"split":[131],"out":[132],"validation":[133],"set":[134],"assist":[136],"manual":[138],"selection.":[140],"Evaluation":[141],"results":[142],"provided":[143],"by":[144],"challenges":[146],"organizers":[147],"demonstrate":[148],"effectiveness":[150],"system.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
