{"id":"https://openalex.org/W4312908873","doi":"https://doi.org/10.1145/3548608.3559304","title":"CRCTTS: Convolution-Recurrent-Convolution Text-to-Speech System","display_name":"CRCTTS: Convolution-Recurrent-Convolution Text-to-Speech System","publication_year":2022,"publication_date":"2022-06-24","ids":{"openalex":"https://openalex.org/W4312908873","doi":"https://doi.org/10.1145/3548608.3559304"},"language":"en","primary_location":{"id":"doi:10.1145/3548608.3559304","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548608.3559304","pdf_url":null,"source":{"id":"https://openalex.org/S4363608876","display_name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","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/A5013231723","display_name":"Kuo Chen","orcid":"https://orcid.org/0000-0003-0095-8545"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuo Chen","raw_affiliation_strings":["Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052764499","display_name":"Xuebin Sun","orcid":"https://orcid.org/0000-0002-4867-2282"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuebin Sun","raw_affiliation_strings":["Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"774","last_page":"777"},"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":0.9980000257492065,"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":0.991100013256073,"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/speech-synthesis","display_name":"Speech synthesis","score":0.8549139499664307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8234462738037109},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.8099977970123291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6398035287857056},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5685213208198547},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5678282380104065},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4520348608493805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42341238260269165},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36921268701553345},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10273587703704834}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8549139499664307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234462738037109},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.8099977970123291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6398035287857056},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5685213208198547},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5678282380104065},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4520348608493805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42341238260269165},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36921268701553345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10273587703704834},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3548608.3559304","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3548608.3559304","pdf_url":null,"source":{"id":"https://openalex.org/S4363608876","display_name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2767052532","https://openalex.org/W2964243274","https://openalex.org/W3015922793"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W3179968364","https://openalex.org/W2043093291"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,60,122],"synthesis":[2,61,121,136],"technology":[3],"has":[4,116],"already":[5],"replaced":[6],"the":[7,41,78,96,105,109,139],"positions":[8],"of":[9,31,132],"Statistical":[10],"Parametric":[11],"Speech":[12],"Synthesis":[13],"(SPSS)":[14],"in":[15,108,130],"text-to-speech":[16],"(TTS)":[17],"field.":[18],"The":[19,112],"end-to-end":[20,59],"model":[21,43,75,102,113,141],"based":[22],"on":[23],"neural":[24],"network,":[25],"does":[26],"not":[27],"require":[28],"a":[29,57],"lot":[30],"domain":[32],"knowledge":[33],"but":[34],"synthesize":[35,46],"more":[36],"natural":[37],"speeches.":[38],"Tacotron":[39,71],"is":[40,51,64],"first":[42],"that":[44,119],"can":[45,120],"speeches":[47],"which":[48,63],"even":[49],"human":[50],"hard":[52],"to":[53,100],"distinguish.":[54],"We":[55,69],"propose":[56],"new":[58],"system":[62],"called":[65],"Convolution-Recurrent-Convolution":[66],"Text-to-Speech":[67],"(CRCTTS).":[68],"chose":[70],"as":[72],"our":[73,101],"baseline":[74,140],"and":[76,87,126,135],"adjust":[77],"architecture":[79],"through":[80],"fully":[81],"Convolution":[82,89],"Neural":[83],"Network":[84],"(CNN)":[85],"module":[86],"Dynamic":[88],"Attention":[90],"(DCA).":[91],"Besides,":[92],"we":[93,114],"also":[94],"introduce":[95],"attention":[97,106],"guided":[98],"mechanism":[99],"for":[103],"accelerating":[104],"alignment":[107],"decoder":[110],"module.":[111],"proposed":[115],"been":[117],"proved":[118],"with":[123,142],"better":[124],"quality":[125],"cost":[127],"less":[128],"time":[129],"terms":[131],"training":[133],"stage":[134,137],"than":[138],"these":[143],"technologies.":[144]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}