{"id":"https://openalex.org/W4283310764","doi":"https://doi.org/10.21437/interspeech.2022-257","title":"Human-in-the-loop Speaker Adaptation for DNN-based Multi-speaker TTS","display_name":"Human-in-the-loop Speaker Adaptation for DNN-based Multi-speaker TTS","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283310764","doi":"https://doi.org/10.21437/interspeech.2022-257"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-257","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-257","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5062213719","display_name":"Kenta Udagawa","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kenta Udagawa","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112904382","display_name":"Yuki Saito","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062213719"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.4861,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.57570035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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/T12031","display_name":"Speech and dialogue systems","score":0.9767000079154968,"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":0.786248505115509},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7723962664604187},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7273763418197632},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6478608846664429},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6269981861114502},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6109078526496887},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5717103481292725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4354909658432007},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4222894310951233},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3594706654548645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.786248505115509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7723962664604187},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7273763418197632},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6478608846664429},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6269981861114502},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6109078526496887},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5717103481292725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4354909658432007},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4222894310951233},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3594706654548645},{"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:10.21437/interspeech.2022-257","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-257","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G3480867415","display_name":null,"funder_award_id":"JPMJPS2011","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2102003408","https://openalex.org/W2156387975","https://openalex.org/W2471520273","https://openalex.org/W2519648275","https://openalex.org/W2619368999","https://openalex.org/W2622263826","https://openalex.org/W2738735766","https://openalex.org/W2788357188","https://openalex.org/W2808706139","https://openalex.org/W2964243274","https://openalex.org/W3023257870","https://openalex.org/W3033411150","https://openalex.org/W3034729383","https://openalex.org/W3081800019","https://openalex.org/W3087999580","https://openalex.org/W3092028330","https://openalex.org/W3096514088","https://openalex.org/W3131643166","https://openalex.org/W3196027980","https://openalex.org/W4235154690","https://openalex.org/W4298857617"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W2206035908","https://openalex.org/W3148366653","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"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,10,14,26,31,55,61,77,85,89,92,111,115,160],"human-in-the-loop":[4,56],"speaker-adaptation":[5,12],"method":[6,35,51,75,135],"for":[7,41,123],"multi-speaker":[8],"text-to-speech.With":[9],"conventional":[11,142],"method,":[13],"target":[15,43,71],"speaker's":[16,72],"embedding":[17,39,97],"vector":[18,40],"is":[19,49,52,153],"extracted":[20],"from":[21,105],"his/her":[22],"reference":[23,47,151],"speech":[24,48,103,152],"using":[25],"speaker":[27,44,161],"encoder":[28,162],"trained":[29],"on":[30,54,91],"speaker-discriminative":[32],"task.However,":[33],"this":[34],"cannot":[36],"obtain":[37],"an":[38,128],"the":[42,46,65,70,96,101,133,141,157],"when":[45],"unavailable.Our":[50],"based":[53],"optimization":[57],"framework,":[58],"which":[59,114],"incorporates":[60],"user":[62,86,116],"to":[63,68,87,140],"explore":[64],"speakerembedding":[66],"space":[67],"find":[69],"embedding.The":[73],"proposed":[74,134],"uses":[76],"sequential":[78],"line":[79,93],"search":[80],"algorithm":[81],"that":[82,132],"repeatedly":[83],"asks":[84],"select":[88],"point":[90],"segment":[94],"in":[95,113,144],"space.To":[98],"efficiently":[99],"choose":[100],"best":[102],"sample":[104],"multiple":[106,120],"stimuli,":[107],"we":[108],"also":[109],"developed":[110],"system":[112],"can":[117,136],"switch":[118],"between":[119],"speakers'":[121],"voices":[122],"each":[124],"phoneme":[125],"while":[126],"looping":[127],"utterance.Experimental":[129],"results":[130],"indicate":[131],"achieve":[137],"comparable":[138],"performance":[139],"one":[143],"objective":[145],"and":[146],"subjective":[147],"evaluations":[148],"even":[149],"if":[150],"not":[154],"used":[155],"as":[156],"input":[158],"of":[159],"directly.":[163]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}