{"id":"https://openalex.org/W1515194102","doi":"https://doi.org/10.21437/interspeech.2012-445","title":"Towards glottal source controllability in expressive speech synthesis","display_name":"Towards glottal source controllability in expressive speech synthesis","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W1515194102","doi":"https://doi.org/10.21437/interspeech.2012-445","mag":"1515194102"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/2584bd61-fee8-4a69-b492-8589f3dd3c71","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Analyse et synth\u00e8se sonores [Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse et synth\u00e8se sonores [Paris]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":["Analyse et synth\u00e8se sonores [Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse et synth\u00e8se sonores [Paris]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":["Analyse et synth\u00e8se sonores [Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse et synth\u00e8se sonores [Paris]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042745853","display_name":"Nicolas Obin","orcid":"https://orcid.org/0000-0002-5236-5306"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Obin","raw_affiliation_strings":["Analyse et synth\u00e8se sonores [Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse et synth\u00e8se sonores [Paris]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Analyse et synth\u00e8se sonores [Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse et synth\u00e8se sonores [Paris]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051480712","display_name":"Juan Manuel Montero","orcid":"https://orcid.org/0000-0002-7908-5400"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan M. Montero","raw_affiliation_strings":["Analyse et synth\u00e8se sonores [Paris]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analyse et synth\u00e8se sonores [Paris]","institution_ids":[]}]}],"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":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1620","last_page":"1623"},"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":0.9970999956130981,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8043575882911682},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.7888023853302002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7465558648109436},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6270198822021484},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4776422083377838},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.4620122015476227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4453763961791992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39064064621925354},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.076144278049469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043575882911682},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.7888023853302002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7465558648109436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6270198822021484},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4776422083377838},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.4620122015476227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4453763961791992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39064064621925354},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.076144278049469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-445","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/2584bd61-fee8-4a69-b492-8589f3dd3c71","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/towards-glottal-source-controllability-in-expressive-speech-synthesis(2584bd61-fee8-4a69-b492-8589f3dd3c71).html","pdf_url":"http://hdl.handle.net/20.500.11820/2584bd61-fee8-4a69-b492-8589f3dd3c71","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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:ec_fundedresources/2584bd61-fee8-4a69-b492-8589f3dd3c71","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/towards-glottal-source-controllability-in-expressive-speech-synthesis(2584bd61-fee8-4a69-b492-8589f3dd3c71).html","pdf_url":"http://hdl.handle.net/20.500.11820/2584bd61-fee8-4a69-b492-8589f3dd3c71","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W1515194102.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W57368184","https://openalex.org/W63438600","https://openalex.org/W191152114","https://openalex.org/W207011259","https://openalex.org/W602985745","https://openalex.org/W1600722501","https://openalex.org/W2024590593","https://openalex.org/W2051457717","https://openalex.org/W2074854222","https://openalex.org/W2403771732"],"related_works":["https://openalex.org/W4254851101","https://openalex.org/W3171007296","https://openalex.org/W2036697162","https://openalex.org/W22115721","https://openalex.org/W2561315646","https://openalex.org/W2332386680","https://openalex.org/W2248621902","https://openalex.org/W2003779889","https://openalex.org/W2211931904","https://openalex.org/W4205698120"],"abstract_inverted_index":{"In":[0],"order":[1,131],"to":[2,16,31,35,42,50,132],"obtain":[3],"more":[4],"human":[5],"like":[6],"sounding":[7],"human-":[8],"machine":[9],"interfaces":[10],"we":[11,40,75,116,141],"must":[12],"first":[13],"be":[14],"able":[15],"give":[17],"them":[18,34],"expressive":[19,95],"capabilities":[20],"in":[21,130],"the":[22,36,53,67,70,79,85,94,100,118,127],"way":[23],"of":[24,56,69,78,87,120],"emotional":[25,113],"and":[26,59,110,123,153],"stylistic":[27],"features":[28,45,152],"so":[29],"as":[30],"closely":[32],"adequate":[33],"intended":[37],"task.":[38],"If":[39],"want":[41],"replicate":[43,52],"those":[44],"it":[46],"is":[47,66],"not":[48],"enough":[49],"merely":[51],"prosodic":[54,151],"information":[55],"fundamental":[57],"frequency":[58],"speaking":[60,109,144],"rhythm.":[61],"The":[62],"proposed":[63],"additional":[64],"layer":[65],"modification":[68],"glottal":[71],"model,":[72],"for":[73,147],"which":[74],"make":[76],"use":[77],"GlottHMM":[80],"parameters.":[81],"This":[82],"paper":[83],"analyzes":[84],"viability":[86],"such":[88],"an":[89],"approach":[90],"by":[91,99],"verifying":[92],"that":[93],"nuances":[96],"are":[97],"captured":[98],"aforementioned":[101],"features,":[102],"obtaining":[103],"95%":[104],"recognition":[105],"rates":[106],"on":[107,112,126,150],"styled":[108],"82%":[111],"speech.":[114],"Then":[115],"evaluate":[117],"effect":[119],"speaker":[121],"bias":[122],"recording":[124],"environment":[125],"source":[128],"modeling":[129],"quantify":[133],"possible":[134],"problems":[135],"when":[136],"analyzing":[137],"multi-speaker":[138],"databases.":[139],"Finally":[140],"propose":[142],"a":[143],"styles":[145],"separation":[146],"Spanish":[148],"based":[149],"check":[154],"its":[155],"perceptual":[156],"significance.":[157]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
