{"id":"https://openalex.org/W3134354180","doi":"https://doi.org/10.1109/icassp39728.2021.9413880","title":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech","display_name":"Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3134354180","doi":"https://doi.org/10.1109/icassp39728.2021.9413880","mag":"3134354180"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413880","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.04088","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072923563","display_name":"Chung-Ming Chien","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chung-Ming Chien","raw_affiliation_strings":["National Taiwan University College of Electrical Engineering and Computer Science","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"National Taiwan University College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084818946","display_name":"Jheng-Hao Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jheng-Hao Lin","raw_affiliation_strings":["National Taiwan University College of Electrical Engineering and Computer Science","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"National Taiwan University College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090229064","display_name":"Chien\u2010Yu Huang","orcid":"https://orcid.org/0009-0008-3346-1870"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-yu Huang","raw_affiliation_strings":["National Taiwan University College of Electrical Engineering and Computer Science","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"National Taiwan University College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034235870","display_name":"Po\u2010Chun Hsu","orcid":"https://orcid.org/0000-0002-6509-9377"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-chun Hsu","raw_affiliation_strings":["National Taiwan University College of Electrical Engineering and Computer Science","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"National Taiwan University College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["National Taiwan University College of Electrical Engineering and Computer Science","National Taiwan University"],"affiliations":[{"raw_affiliation_string":"National Taiwan University College of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072923563"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52068065,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"8588","last_page":"8592"},"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":0.9966999888420105,"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/T10860","display_name":"Speech and Audio Processing","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.746709942817688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7230882048606873},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6738723516464233},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.642566978931427},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.574012815952301},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5397151112556458},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5327306985855103},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5174039602279663},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4463222026824951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36695700883865356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3500533103942871},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07640382647514343}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.746709942817688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7230882048606873},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6738723516464233},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.642566978931427},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.574012815952301},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5397151112556458},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5327306985855103},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5174039602279663},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4463222026824951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36695700883865356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3500533103942871},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07640382647514343},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413880","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"},{"id":"pmh:oai:arXiv.org:2103.04088","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.04088","pdf_url":"https://arxiv.org/pdf/2103.04088","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3134354180","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.04088.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.04088","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.04088","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/t4w3-2143","is_oa":true,"landing_page_url":"https://doi.org/10.17023/t4w3-2143","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.04088","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.04088","pdf_url":"https://arxiv.org/pdf/2103.04088","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3134354180.pdf","grobid_xml":"https://content.openalex.org/works/W3134354180.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2747874407","https://openalex.org/W2890964092","https://openalex.org/W2949382160","https://openalex.org/W2962788625","https://openalex.org/W2963192573","https://openalex.org/W2963272440","https://openalex.org/W2963432880","https://openalex.org/W2963568578","https://openalex.org/W2963691546","https://openalex.org/W2963912924","https://openalex.org/W2964243274","https://openalex.org/W2972659941","https://openalex.org/W3010916717","https://openalex.org/W3015826515","https://openalex.org/W3096086473","https://openalex.org/W3135644023","https://openalex.org/W3162794600","https://openalex.org/W6743149223","https://openalex.org/W6748588790","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6755300632","https://openalex.org/W6792650190"],"related_works":["https://openalex.org/W3161704465","https://openalex.org/W2939913319","https://openalex.org/W2165340520","https://openalex.org/W2951130829","https://openalex.org/W2885553183","https://openalex.org/W3015484365","https://openalex.org/W3135654121","https://openalex.org/W2269033948","https://openalex.org/W2972705840","https://openalex.org/W2772376594","https://openalex.org/W2963912924","https://openalex.org/W3096456328","https://openalex.org/W3105867580","https://openalex.org/W3025035610","https://openalex.org/W3046492833","https://openalex.org/W1610914625","https://openalex.org/W3011209123","https://openalex.org/W2899351468","https://openalex.org/W3044308976","https://openalex.org/W2091802891"],"abstract_inverted_index":{"The":[0,59],"few-shot":[1,76],"multi-speaker":[2],"multi-style":[3],"voice":[4,12,53],"cloning":[5],"task":[6],"is":[7],"to":[8,17,37],"synthesize":[9],"utterances":[10],"with":[11,64],"and":[13,35,40,67,78],"speaking":[14],"style":[15],"similar":[16],"a":[18,23],"reference":[19,25],"speaker":[20,33,42,69],"given":[21],"only":[22],"few":[24],"samples.":[26],"In":[27],"this":[28],"work,":[29],"we":[30],"investigate":[31],"different":[32,45],"representations":[34,70],"proposed":[36],"integrate":[38],"pretrained":[39,51,66],"learnable":[41,68],"representations.":[43],"Among":[44],"types":[46],"of":[47,86],"embeddings,":[48],"the":[49,56,83,87],"embedding":[50],"by":[52],"conversion":[54],"achieves":[55],"best":[57],"performance.":[58],"FastSpeech":[60],"2":[61],"model":[62],"combined":[63],"both":[65],"shows":[71],"great":[72],"generalization":[73],"ability":[74],"on":[75],"speakers":[77],"achieved":[79],"2nd":[80],"place":[81],"in":[82],"one-shot":[84],"track":[85],"ICASSP":[88],"2021":[89],"M2VoC":[90],"challenge.":[91]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
