{"id":"https://openalex.org/W3136358483","doi":"https://doi.org/10.1109/access.2021.3065736","title":"Enhancing Local Dependencies for Transformer-Based Text-to-Speech via Hybrid Lightweight Convolution","display_name":"Enhancing Local Dependencies for Transformer-Based Text-to-Speech via Hybrid Lightweight Convolution","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3136358483","doi":"https://doi.org/10.1109/access.2021.3065736","mag":"3136358483"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3065736","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3065736","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09376936.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09376936.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040153479","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0001-8452-9339"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China","Institute of Robotics, Zhejiang University, Yuyao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Institute of Robotics, Zhejiang University, Yuyao, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088400668","display_name":"Ting He","orcid":"https://orcid.org/0000-0003-1070-7483"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting He","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China","Institute of Robotics, Zhejiang University, Yuyao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Institute of Robotics, Zhejiang University, Yuyao, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100648031","display_name":"Xu Li","orcid":"https://orcid.org/0000-0001-7874-629X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Xu","raw_affiliation_strings":["College of Electrical Engineering, Zhejiang University, Hangzhou, China","Institute of Robotics, Zhejiang University, Yuyao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Institute of Robotics, Zhejiang University, Yuyao, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.1365,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5075607,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"42762","last_page":"42770"},"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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":0.998199999332428,"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":0.8003722429275513},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7850478291511536},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6058238744735718},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5476863980293274},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4646771550178528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3826504647731781},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1341807246208191},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10551261901855469},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08508378267288208},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0691506564617157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003722429275513},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7850478291511536},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6058238744735718},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5476863980293274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4646771550178528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3826504647731781},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1341807246208191},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10551261901855469},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08508378267288208},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0691506564617157},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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":2,"locations":[{"id":"doi:10.1109/access.2021.3065736","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3065736","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09376936.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:755acbf5ce35445a850c7f99f462198d","is_oa":true,"landing_page_url":"https://doaj.org/article/755acbf5ce35445a850c7f99f462198d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 42762-42770 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3065736","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3065736","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09376936.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8613538274","display_name":null,"funder_award_id":"K11801","funder_id":"https://openalex.org/F4320322927","funder_display_name":"Zhejiang University"}],"funders":[{"id":"https://openalex.org/F4320322927","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3136358483.pdf","grobid_xml":"https://content.openalex.org/works/W3136358483.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2107860279","https://openalex.org/W2194775991","https://openalex.org/W2519091744","https://openalex.org/W2567070169","https://openalex.org/W2613904329","https://openalex.org/W2767052532","https://openalex.org/W2896457183","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2905016804","https://openalex.org/W2908336025","https://openalex.org/W2946200149","https://openalex.org/W2949382160","https://openalex.org/W2952809536","https://openalex.org/W2962739369","https://openalex.org/W2963300588","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963534259","https://openalex.org/W2963564796","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963970792","https://openalex.org/W2964110616","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964265128","https://openalex.org/W2970597249","https://openalex.org/W2970730223","https://openalex.org/W2989571009","https://openalex.org/W3007580377","https://openalex.org/W3015922793","https://openalex.org/W3016160783","https://openalex.org/W3096442195","https://openalex.org/W4295253143","https://openalex.org/W4298174729","https://openalex.org/W4298857617","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6640212811","https://openalex.org/W6674330103","https://openalex.org/W6731370813","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6745569068","https://openalex.org/W6748573829","https://openalex.org/W6749489859","https://openalex.org/W6751097180","https://openalex.org/W6755207826","https://openalex.org/W6756197946","https://openalex.org/W6757585730","https://openalex.org/W6763701032","https://openalex.org/W6763832098","https://openalex.org/W6769513855","https://openalex.org/W6770855403","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W4387838477","https://openalex.org/W2067193074","https://openalex.org/W2182785089","https://openalex.org/W4312178642","https://openalex.org/W2375093801","https://openalex.org/W3107426390","https://openalex.org/W1534368937","https://openalex.org/W2112284452","https://openalex.org/W4312624109","https://openalex.org/W3175683656"],"abstract_inverted_index":{"Owing":[0],"to":[1,88],"the":[2,6,23,53,66,86,90,111,127],"powerful":[3],"self-attention":[4,32,87,130],"mechanism,":[5],"Transformer":[7],"network":[8],"has":[9,19],"achieved":[10],"considerable":[11],"successes":[12],"across":[13],"many":[14],"sequence":[15,145],"modeling":[16,41,146],"tasks":[17],"and":[18,82,107,131],"become":[20],"one":[21],"of":[22,79,129],"most":[24],"popular":[25],"methods":[26],"in":[27,34,40,104],"text-to-speech":[28],"(TTS).":[29],"The":[30,93],"vanilla":[31],"excels":[33],"capturing":[35],"long-range":[36],"dependencies":[37,44],"but":[38],"suffers":[39],"stable":[42],"short-range":[43],"that":[45,97,117],"are":[46,57],"quite":[47],"important":[48],"for":[49,74,143],"speech":[50],"synthesis":[51],"where":[52],"local":[54,77],"audio":[55],"signals":[56],"highly":[58],"correlated.":[59],"To":[60],"address":[61],"this":[62,137],"problem,":[63],"we":[64,114],"propose":[65],"hybrid":[67,133],"lightweight":[68,134],"convolution":[69],"(HLC),":[70],"which":[71],"is":[72,139],"responsible":[73],"fully":[75],"exploiting":[76],"structures":[78],"a":[80,118],"sequence,":[81],"combine":[83],"it":[84],"with":[85],"improve":[89],"Transformer-based":[91],"TTS.":[92],"experimental":[94],"results":[95],"show":[96],"our":[98],"modified":[99],"model":[100,122],"obtains":[101],"better":[102],"performance":[103],"both":[105],"objective":[106],"subjective":[108],"evaluations.":[109],"At":[110],"same":[112],"time,":[113],"also":[115,140],"demonstrate":[116],"more":[119],"compact":[120],"TTS":[121],"may":[123],"be":[124],"built":[125],"through":[126],"combination":[128],"proposed":[132],"convolution.":[135],"Besides,":[136],"method":[138],"potentially":[141],"adaptable":[142],"other":[144],"tasks.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}