{"id":"https://openalex.org/W3015484365","doi":"https://doi.org/10.1109/icassp40776.2020.9053642","title":"Speaker Adaptation of a Multilingual Acoustic Model for Cross-Language Synthesis","display_name":"Speaker Adaptation of a Multilingual Acoustic Model for Cross-Language Synthesis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015484365","doi":"https://doi.org/10.1109/icassp40776.2020.9053642","mag":"3015484365"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/06eba81e-f1bb-4c2d-999b-3cdbe5e305ea","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039529498","display_name":"Ivan Himawan","orcid":"https://orcid.org/0000-0003-3848-244X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ivan Himawan","raw_affiliation_strings":["ObEN, Inc., Pasadena, California, USA"],"affiliations":[{"raw_affiliation_string":"ObEN, Inc., Pasadena, California, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sandesh Aryal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sandesh Aryal","raw_affiliation_strings":["ObEN, Inc., Pasadena, California, USA"],"affiliations":[{"raw_affiliation_string":"ObEN, Inc., Pasadena, California, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070531353","display_name":"Iris Chuoying Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iris Ouyang","raw_affiliation_strings":["ObEN, Inc., Pasadena, California, USA"],"affiliations":[{"raw_affiliation_string":"ObEN, Inc., Pasadena, California, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112519050","display_name":"Sam Seok Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Kang","raw_affiliation_strings":["ObEN, Inc., Pasadena, California, USA"],"affiliations":[{"raw_affiliation_string":"ObEN, Inc., Pasadena, California, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003588321","display_name":"Pierre Lanchantin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Lanchantin","raw_affiliation_strings":["ObEN, Inc., Pasadena, California, USA"],"affiliations":[{"raw_affiliation_string":"ObEN, Inc., Pasadena, California, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5039529498"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4465,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91102321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7629","last_page":"7633"},"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":0.9962000250816345,"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/T10028","display_name":"Topic Modeling","score":0.9950000047683716,"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":0.8511813879013062},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6649987101554871},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5914045572280884},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.47635650634765625},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46858495473861694},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4478762745857239},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.43433430790901184},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4313221871852875},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.424574613571167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38586610555648804},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.32660067081451416},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08612892031669617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8511813879013062},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6649987101554871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5914045572280884},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.47635650634765625},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46858495473861694},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4478762745857239},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.43433430790901184},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4313221871852875},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.424574613571167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38586610555648804},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.32660067081451416},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08612892031669617},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/06eba81e-f1bb-4c2d-999b-3cdbe5e305ea","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/06eba81e-f1bb-4c2d-999b-3cdbe5e305ea","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Himawan, I, Aryal, S, Ouyang, I, Kang, S, Lanchantin, P & King, S 2020, Speaker adaptation of a multilingual acoustic model for cross-language synthesis. in 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings., 9053642, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2020-May, Institute of Electrical and Electronics Engineers, pp. 7629-7633, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9053642","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/06eba81e-f1bb-4c2d-999b-3cdbe5e305ea","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/06eba81e-f1bb-4c2d-999b-3cdbe5e305ea","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/06eba81e-f1bb-4c2d-999b-3cdbe5e305ea","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/06eba81e-f1bb-4c2d-999b-3cdbe5e305ea","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Himawan, I, Aryal, S, Ouyang, I, Kang, S, Lanchantin, P & King, S 2020, Speaker adaptation of a multilingual acoustic model for cross-language synthesis. in 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020 - Proceedings., 9053642, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2020-May, Institute of Electrical and Electronics Engineers, pp. 7629-7633, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9053642","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1492383498","https://openalex.org/W1995565802","https://openalex.org/W2025638820","https://openalex.org/W2064875742","https://openalex.org/W2081254602","https://openalex.org/W2114010348","https://openalex.org/W2139751012","https://openalex.org/W2401698713","https://openalex.org/W2471520273","https://openalex.org/W2494654097","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2591927543","https://openalex.org/W2598638573","https://openalex.org/W2746498480","https://openalex.org/W2759925408","https://openalex.org/W2787685498","https://openalex.org/W2788357188","https://openalex.org/W2794235490","https://openalex.org/W2808706139","https://openalex.org/W2901997113","https://openalex.org/W2915046899","https://openalex.org/W2949382160","https://openalex.org/W2963192573","https://openalex.org/W2963432880","https://openalex.org/W2963534259","https://openalex.org/W2963609956","https://openalex.org/W2963691546","https://openalex.org/W2963964591","https://openalex.org/W2964281804","https://openalex.org/W2972473628","https://openalex.org/W2972921407","https://openalex.org/W4298857617","https://openalex.org/W6629609042","https://openalex.org/W6712757316","https://openalex.org/W6732429163","https://openalex.org/W6734815144","https://openalex.org/W6744965914","https://openalex.org/W6745569068","https://openalex.org/W6748588790","https://openalex.org/W6749489859","https://openalex.org/W6752888775","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Several":[0],"studies":[1],"have":[2],"shown":[3],"promising":[4],"results":[5],"in":[6,49,63,105,118,161,165,177],"adapting":[7],"DNN-based":[8],"acoustic":[9],"models":[10,37],"as":[11],"a":[12,27,84,88,95,101,119,134,184],"mechanism":[13],"to":[14,41,60,158],"transfer":[15],"characteristics":[16],"from":[17,94,133,183],"pre-trained":[18],"models.":[19],"One":[20],"such":[21],"example":[22],"is":[23,59,110,156],"speaker":[24,136,154,176,186],"adaptation":[25,51,131,155],"using":[26,66,87,113],"small":[28],"amount":[29],"of":[30,72,75,92,98,137,152,187],"data,":[31],"where":[32],"fine-tuning":[33],"has":[34],"helped":[35],"train":[36],"that":[38,45,90,148,178],"extrapolate":[39],"well":[40],"diverse":[42],"linguistic":[43],"contexts":[44],"are":[46],"not":[47],"present":[48],"the":[50,54,67,73,114,123,138,142,149,162,166,174,188],"data.":[52,77],"In":[53],"current":[55],"work,":[56],"our":[57],"objective":[58],"synthesize":[61,159],"speech":[62,160],"different":[64],"languages":[65],"target":[68,115,124,139,163,167,175,189],"speaker's":[69,116,168],"voice,":[70,169],"regardless":[71],"language":[74,120,140,190],"their":[76],"To":[78],"achieve":[79],"this":[80],"goal,":[81],"we":[82],"create":[83],"multilingual":[85],"model":[86,109,193],"corpus":[89],"consists":[91],"recordings":[93,117],"large":[96],"number":[97],"monolingual":[99],"and":[100],"few":[102],"bilingual":[103],"speakers":[104],"multiple":[106],"languages.":[107],"The":[108,144],"then":[111],"adapted":[112],"other":[121],"than":[122],"language.":[125,179],"We":[126],"also":[127],"explore":[128],"if":[129],"additional":[130],"data":[132,171,182],"native":[135,185],"improves":[141],"performance.":[143,194],"subjective":[145],"evaluation":[146],"shows":[147],"proposed":[150],"approach":[151],"cross-language":[153],"able":[157],"language,":[164],"without":[170],"spoken":[172],"by":[173],"Also,":[180],"extra":[181],"can":[191],"improve":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}