{"id":"https://openalex.org/W4224301045","doi":"https://doi.org/10.21437/interspeech.2022-11278","title":"Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation","display_name":"Cross-Speaker Emotion Transfer for Low-Resource Text-to-Speech Using Non-Parallel Voice Conversion with Pitch-Shift Data Augmentation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4224301045","doi":"https://doi.org/10.21437/interspeech.2022-11278"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11278","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11278","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":"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/A5064331370","display_name":"Ryo Terashima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryo Terashima","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100556054","display_name":"Ryuichi Yamamoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryuichi Yamamoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104035145","display_name":"Eunwoo Song","orcid":"https://orcid.org/0000-0003-0642-7083"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunwoo Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011940388","display_name":"Yuma Shirahata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuma Shirahata","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032657615","display_name":"Hyun-Wook Yoon","orcid":"https://orcid.org/0000-0002-2849-4140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyun-Wook Yoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101480212","display_name":"Jae-Min Kim","orcid":"https://orcid.org/0000-0002-7705-6462"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jae-Min Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057222718","display_name":"Kentaro Tachibana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kentaro Tachibana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3018","last_page":"3022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9919000267982483,"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":0.9919000267982483,"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/T10860","display_name":"Speech and Audio Processing","score":0.9876000285148621,"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/naturalness","display_name":"Naturalness","score":0.8967101573944092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7589510679244995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7297494411468506},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6531971096992493},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5268862247467041},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.45781224966049194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3084920644760132}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8967101573944092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7589510679244995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7297494411468506},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6531971096992493},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5268862247467041},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45781224966049194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3084920644760132},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11278","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11278","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":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,71,82],"via":[2],"voice":[3],"conversion":[4],"(VC)":[5],"has":[6,58],"been":[7],"successfully":[8],"applied":[9],"to":[10,38],"low-resource":[11,52],"expressive":[12,56],"text-to-speech":[13],"(TTS)":[14],"when":[15,103],"only":[16,104],"neutral":[17,111],"data":[18,48,70,81,112],"for":[19,32,96],"the":[20,26,45,84,108,127],"target":[21,109],"speaker":[22],"are":[23,113],"available.":[24,114],"Although":[25],"quality":[27],"of":[28,47,86,89,107],"VC":[29,42,77,98],"is":[30,36,49],"crucial":[31],"this":[33,64],"approach,":[34],"it":[35,92],"challenging":[37],"learn":[39],"a":[40,68,87,120],"stable":[41],"model":[43],"because":[44],"amount":[46],"limited":[50],"in":[51],"scenarios,":[53],"and":[54,76,99,132],"highly":[55],"speech":[57],"large":[59],"acoustic":[60],"variety.":[61],"To":[62],"address":[63],"issue,":[65],"we":[66],"propose":[67],"novel":[69],"method":[72,129],"that":[73,119],"combines":[74],"pitch-shifting":[75],"techniques.":[78],"Because":[79],"pitch-shift":[80],"enables":[83],"coverage":[85],"variety":[88],"pitch":[90],"dynamics,":[91],"greatly":[93],"stabilizes":[94],"training":[95],"both":[97],"TTS":[100,124],"models,":[101],"even":[102],"1,000":[105],"utterances":[106],"speaker's":[110],"Subjective":[115],"test":[116],"results":[117],"showed":[118],"FastSpeech":[121],"2-based":[122],"emotional":[123,133],"system":[125],"with":[126,136],"proposed":[128],"improved":[130],"naturalness":[131],"similarity":[134],"compared":[135],"conventional":[137],"methods.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}