{"id":"https://openalex.org/W4319585922","doi":"https://doi.org/10.1109/iscslp57327.2022.10038221","title":"Low-Resource Speech Synthesis with Speaker-Aware Embedding","display_name":"Low-Resource Speech Synthesis with Speaker-Aware Embedding","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319585922","doi":"https://doi.org/10.1109/iscslp57327.2022.10038221"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10038221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038221","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5016250453","display_name":"Li-Jen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li-Jen Yang","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Taiwan","Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060200564","display_name":"I-Ping Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I-Ping Yeh","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Graduate Degree Program of Cybersecurity,Taiwan","Graduate Degree Program of Cybersecurity, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Graduate Degree Program of Cybersecurity,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Graduate Degree Program of Cybersecurity, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Taiwan","Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electrical and Computer Engineering,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"235","last_page":"239"},"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":0.996399998664856,"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":0.9962000250816345,"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":0.8174417018890381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6813026666641235},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6564900875091553},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5904741287231445},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4946598708629608},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48502272367477417},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45814061164855957},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4530368745326996},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.43513134121894836},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.432468056678772},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4175020158290863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3729649782180786},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3653830289840698},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3113471269607544},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07366150617599487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174417018890381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6813026666641235},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6564900875091553},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5904741287231445},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4946598708629608},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48502272367477417},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45814061164855957},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4530368745326996},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.43513134121894836},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.432468056678772},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4175020158290863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3729649782180786},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3653830289840698},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3113471269607544},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07366150617599487},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/iscslp57327.2022.10038221","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10038221","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2014506068","https://openalex.org/W2046056978","https://openalex.org/W2107860279","https://openalex.org/W2150769028","https://openalex.org/W2888473984","https://openalex.org/W2890964092","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2962780374","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W3015338123","https://openalex.org/W3039832962","https://openalex.org/W3095545636","https://openalex.org/W3116256056","https://openalex.org/W3117789470","https://openalex.org/W3138043709","https://openalex.org/W3161109662","https://openalex.org/W3198347216","https://openalex.org/W4224925597","https://openalex.org/W4225407673","https://openalex.org/W4301371414","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6739901393","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6790220310","https://openalex.org/W6796464841","https://openalex.org/W6803547063"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Speech":[0],"synthesis":[1,37,90,144],"has":[2],"been":[3,18],"successfully":[4],"exploited":[5],"for":[6,43],"mapping":[7],"from":[8,23,117],"text":[9],"sequence":[10],"to":[11,130,147],"speech":[12,36,44,61,89,143],"waveform":[13],"where":[14],"high-resource":[15],"languages":[16,40],"have":[17],"well":[19],"studied":[20],"and":[21,125,160],"learned":[22],"a":[24,72,87,108,114,121,131],"large":[25],"amount":[26],"of":[27,52,79,120,151,156],"text-speech":[28],"paired":[29],"data":[30,54,119],"in":[31,46,68,77,154],"public-domain":[32],"corpora.":[33],"However,":[34],"developing":[35],"under":[38,63,91],"low-resource":[39,64,92,141],"is":[41,55,66,74,104],"challenging":[42],"communication":[45],"local":[47],"regions":[48],"since":[49],"the":[50,59,128,149],"collection":[51],"training":[53],"expensive.":[56],"In":[57],"particular,":[58],"speaker-aware":[60,88,109,152],"generation":[62],"settings":[65,93],"crucial":[67],"real":[69],"world.":[70],"Such":[71],"problem":[73],"increasingly":[75],"difficult":[76],"case":[78],"very":[80,135],"limited":[81,136],"speaker-specific":[82,137],"data.":[83],"This":[84],"paper":[85],"presents":[86],"based":[94],"on":[95,140],"an":[96],"encoder-decoder":[97],"framework":[98],"by":[99,106],"using":[100],"transformer.":[101],"Knowledge":[102],"transfer":[103],"performed":[105],"incorporating":[107],"embedding":[110],"through":[111],"first":[112],"learning":[113],"pretrained":[115],"transformer":[116,129,153],"multi-speaker":[118],"low-populated":[122],"spoken":[123],"language":[124],"then":[126],"fine-tuning":[127],"target":[132],"speaker":[133],"with":[134],"embeddings.":[138],"Experiments":[139],"Taiwanese":[142],"are":[145],"evaluated":[146],"show":[148],"merit":[150],"terms":[155],"Mel":[157],"cepstral":[158],"distortion":[159],"mean":[161],"opinion":[162],"score.":[163]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
