{"id":"https://openalex.org/W2143933318","doi":"https://doi.org/10.1186/1687-4722-2012-21","title":"Speaker-dependent model interpolation for statistical emotional speech synthesis","display_name":"Speaker-dependent model interpolation for statistical emotional speech synthesis","publication_year":2012,"publication_date":"2012-08-16","ids":{"openalex":"https://openalex.org/W2143933318","doi":"https://doi.org/10.1186/1687-4722-2012-21","mag":"2143933318"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2012-21","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-21","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-21","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-21","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104636247","display_name":"Chih\u2010Yu Hsu","orcid":"https://orcid.org/0000-0003-1074-8170"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chih-Yu Hsu","raw_affiliation_strings":["Department of Computer Science and Engineering, National Sun Yat-Sen University, 70 Lien-Hai Road, Kaohsiung, 800, Taiwan","Department of Computer Science and Engineering, National Sun Yat-sen University,  Kaohsiung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, National Sun Yat-Sen University, 70 Lien-Hai Road, Kaohsiung, 800, Taiwan","institution_ids":["https://openalex.org/I142974352"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, National Sun Yat-sen University,  Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087434278","display_name":"Chia-Ping Chen","orcid":"https://orcid.org/0000-0002-7022-3061"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Ping Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, National Sun Yat-Sen University, 70 Lien-Hai Road, Kaohsiung, 800, Taiwan","Department of Computer Science and Engineering, National Sun Yat-sen University,  Kaohsiung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, National Sun Yat-Sen University, 70 Lien-Hai Road, Kaohsiung, 800, Taiwan","institution_ids":["https://openalex.org/I142974352"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, National Sun Yat-sen University,  Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5104636247"],"corresponding_institution_ids":["https://openalex.org/I142974352"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.2844,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84076343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2012","issue":"1","first_page":null,"last_page":null},"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":0.9994999766349792,"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":0.9976999759674072,"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":0.8319882154464722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7016655802726746},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6656830906867981},{"id":"https://openalex.org/keywords/mahalanobis-distance","display_name":"Mahalanobis distance","score":0.6654981970787048},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.6615757942199707},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.623333215713501},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5649455189704895},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5552887320518494},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5455079674720764},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5222300291061401},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4236743450164795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37334489822387695},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09481543302536011},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06760650873184204}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8319882154464722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016655802726746},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6656830906867981},{"id":"https://openalex.org/C1921717","wikidata":"https://www.wikidata.org/wiki/Q1334846","display_name":"Mahalanobis distance","level":2,"score":0.6654981970787048},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6615757942199707},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.623333215713501},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5649455189704895},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5552887320518494},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5455079674720764},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5222300291061401},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4236743450164795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37334489822387695},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09481543302536011},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06760650873184204},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/1687-4722-2012-21","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-21","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-21","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2012-21","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-21","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-21","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2143933318.pdf","grobid_xml":"https://content.openalex.org/works/W2143933318.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W11625191","https://openalex.org/W39968598","https://openalex.org/W1486632395","https://openalex.org/W1512429158","https://openalex.org/W1600722501","https://openalex.org/W1962947832","https://openalex.org/W2036233992","https://openalex.org/W2039800941","https://openalex.org/W2042600255","https://openalex.org/W2049633694","https://openalex.org/W2053031163","https://openalex.org/W2085013480","https://openalex.org/W2087110403","https://openalex.org/W2095437083","https://openalex.org/W2100441082","https://openalex.org/W2125838338","https://openalex.org/W2129142580","https://openalex.org/W2133300417","https://openalex.org/W2150658333","https://openalex.org/W2153914468","https://openalex.org/W2160379050","https://openalex.org/W2161135987","https://openalex.org/W2161736993","https://openalex.org/W2161855744","https://openalex.org/W2166823384","https://openalex.org/W2228674556","https://openalex.org/W2296704011","https://openalex.org/W2599301895","https://openalex.org/W2604216173","https://openalex.org/W2915628810","https://openalex.org/W3142087749"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2108985546","https://openalex.org/W2038801705","https://openalex.org/W2077992636","https://openalex.org/W2279374969","https://openalex.org/W1537411440","https://openalex.org/W290673751","https://openalex.org/W2017702615","https://openalex.org/W2147186888","https://openalex.org/W2024201202"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3,47],"propose":[4,48],"a":[5,36,51,58],"speaker-dependent":[6],"model":[7,23,32,41],"interpolation":[8,44,84],"method":[9,85],"for":[10],"statistical":[11],"emotional":[12,31,91,111],"speech":[13,112],"synthesis.":[14],"The":[15,82],"basic":[16],"idea":[17],"is":[18,57,103],"to":[19,49,72,108],"combine":[20],"the":[21,26,74,78,90,93,96,106,110,114,118],"neutral":[22],"set":[24,33],"of":[25,38,113,120],"target":[27,97,115],"speaker":[28,98],"and":[29,43,95,123],"an":[30],"selected":[34],"from":[35],"pool":[37],"speakers.":[39],"For":[40],"selection":[42],"weight":[45],"determination,":[46],"use":[50],"novel":[52],"monophone-based":[53],"Mahalanobis":[54],"distance,":[55],"which":[56],"proper":[59],"distance":[60],"measure":[61],"between":[62],"two":[63],"Hidden":[64],"Markov":[65],"Model":[66],"sets.":[67],"We":[68],"design":[69],"Latin-square":[70],"evaluation":[71],"reduce":[73],"systematic":[75],"bias":[76],"in":[77],"subjective":[79],"listening":[80],"tests.":[81],"proposed":[83],"achieves":[86],"sound":[87],"performance":[88,102],"on":[89],"expressiveness,":[92],"naturalness,":[94],"similarity.":[99],"Moreover,":[100],"such":[101],"achieved":[104],"without":[105],"need":[107],"collect":[109],"speaker,":[116],"saving":[117],"cost":[119],"data":[121],"collection":[122],"labeling.":[124]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}