{"id":"https://openalex.org/W2082426107","doi":"https://doi.org/10.1109/icassp.2013.6639195","title":"Speaker-independent style conversion for HMM-based expressive speech synthesis","display_name":"Speaker-independent style conversion for HMM-based expressive speech synthesis","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2082426107","doi":"https://doi.org/10.1109/icassp.2013.6639195","mag":"2082426107"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5076754533","display_name":"Hiroki Kanagawa","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroki Kanagawa","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022405100","display_name":"Takao Kobayashi","orcid":"https://orcid.org/0000-0003-0387-8030"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Kobayashi","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.2288,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.49719408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7864","last_page":"7868"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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/T11309","display_name":"Music and Audio Processing","score":0.9901999831199646,"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":0.8496831655502319},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7715002298355103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7304215431213379},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6316564083099365},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6283996105194092},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6220862865447998},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.598061203956604},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4880737066268921},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45834729075431824},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4498410224914551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31895169615745544}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8496831655502319},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7715002298355103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7304215431213379},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6316564083099365},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6283996105194092},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6220862865447998},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.598061203956604},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4880737066268921},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45834729075431824},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4498410224914551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31895169615745544},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639195","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1573140883","display_name":"Research on advanced robust speech synthesis and its applications to multi-lingual speech communication","funder_award_id":"24300071","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1564152904","https://openalex.org/W1599512239","https://openalex.org/W1984905644","https://openalex.org/W2000513720","https://openalex.org/W2002342963","https://openalex.org/W2048973497","https://openalex.org/W2049686551","https://openalex.org/W2081976287","https://openalex.org/W2097544856","https://openalex.org/W2106792148","https://openalex.org/W2148846882","https://openalex.org/W2150791533","https://openalex.org/W2153914468","https://openalex.org/W2161736993","https://openalex.org/W6633741138","https://openalex.org/W6681821128"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2206035908","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2024201202","https://openalex.org/W2535215250"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,59,90],"technique":[4,23],"for":[5],"creating":[6],"target":[7,13,76],"speaker's":[8,14,61],"expressive-style":[9],"model":[10,73],"from":[11],"the":[12,27,54,67,71,75,84,97,102,110,113,119],"neutral":[15,44],"style":[16,28,68,77,114,124],"speech":[17,20,47,82],"in":[18,39,116],"HMM-based":[19],"synthesis.":[21],"The":[22],"is":[24],"based":[25],"on":[26],"adaptation":[29],"using":[30,41],"linear":[31],"transforms":[32],"where":[33],"speaker-independent":[34],"transformation":[35,56],"matrices":[36,57],"are":[37],"estimated":[38],"advance":[40],"pairs":[42],"of":[43,49,70,83,112,118],"and":[45,123],"target-style":[46,81],"data":[48],"multiple":[50],"speakers.":[51,106],"By":[52],"applying":[53],"obtained":[55],"to":[58,74,100],"new":[60],"neutral-style":[62],"model,":[63],"we":[64,88],"can":[65],"convert":[66],"expressivity":[69],"acoustic":[72,103],"without":[78],"preparing":[79],"any":[80],"speaker.":[85],"In":[86],"addition,":[87],"introduce":[89],"speaker":[91,121],"adaptive":[92],"training":[93],"(SAT)":[94],"framework":[95],"into":[96],"transform":[98],"estimation":[99],"reduce":[101],"difference":[104],"among":[105],"We":[107],"subjectively":[108],"evaluate":[109],"performance":[111],"conversion":[115],"terms":[117],"naturalness,":[120],"similarity,":[122],"reproducibility.":[125]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
