{"id":"https://openalex.org/W2095723991","doi":"https://doi.org/10.1109/icassp.2011.5947410","title":"Continuous F0 in the source-excitation generation for HMM-based TTS: Do we need voiced/unvoiced classification?","display_name":"Continuous F0 in the source-excitation generation for HMM-based TTS: Do we need voiced/unvoiced classification?","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2095723991","doi":"https://doi.org/10.1109/icassp.2011.5947410","mag":"2095723991"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5071418947","display_name":"Javier Latorre","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":["Toshiba Research Europe Ltd.,, Cambridge Research Laboratory, UK","Toshiba Research Europe Ltd. Cambridge Research Laboratory, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd.,, Cambridge Research Laboratory, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Research Europe Ltd. Cambridge Research Laboratory, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Mark J.F. Gales","raw_affiliation_strings":["Toshiba Research Europe Ltd.,, Cambridge Research Laboratory, UK","Toshiba Research Europe Ltd. Cambridge Research Laboratory, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd.,, Cambridge Research Laboratory, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Research Europe Ltd. Cambridge Research Laboratory, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004649927","display_name":"Sabine Buchholz","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Sabine Buchholz","raw_affiliation_strings":["Toshiba Research Europe Ltd.,, Cambridge Research Laboratory, UK","Toshiba Research Europe Ltd. Cambridge Research Laboratory, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd.,, Cambridge Research Laboratory, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Research Europe Ltd. Cambridge Research Laboratory, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111076409","display_name":"Kate Knill","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Kate Knill","raw_affiliation_strings":["Toshiba Research Europe Ltd.,, Cambridge Research Laboratory, UK","Toshiba Research Europe Ltd. Cambridge Research Laboratory, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd.,, Cambridge Research Laboratory, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Research Europe Ltd. Cambridge Research Laboratory, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113811305","display_name":"Masatsune Tamura","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masatsune Tamura","raw_affiliation_strings":["Toshiba Corporate Research & Development Center, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Corporate Research & Development Center, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018533235","display_name":"Yamato Ohtani","orcid":"https://orcid.org/0009-0009-2961-2821"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yamato Ohtani","raw_affiliation_strings":["Toshiba Corporate Research & Development Center, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Corporate Research & Development Center, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112250968","display_name":"Masami Akamine","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masami Akamine","raw_affiliation_strings":["Toshiba Corporate Research & Development Center, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Corporate Research & Development Center, Japan","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4724","last_page":"4727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9987999796867371,"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/speech-recognition","display_name":"Speech recognition","score":0.7097127437591553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6648278832435608},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6424466967582703},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5364212989807129},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5299250483512878},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4782337546348572},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4684838056564331},{"id":"https://openalex.org/keywords/excitation","display_name":"Excitation","score":0.44519996643066406},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4232894778251648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4181995987892151},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41745492815971375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1951344609260559},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10424253344535828},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09495440125465393},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0851936936378479}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7097127437591553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6648278832435608},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6424466967582703},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5364212989807129},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5299250483512878},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4782337546348572},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4684838056564331},{"id":"https://openalex.org/C83581075","wikidata":"https://www.wikidata.org/wiki/Q1361503","display_name":"Excitation","level":2,"score":0.44519996643066406},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4232894778251648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4181995987892151},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41745492815971375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1951344609260559},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10424253344535828},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09495440125465393},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0851936936378479},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:345960","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/345960/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W200094172","https://openalex.org/W1935012542","https://openalex.org/W2049686551","https://openalex.org/W2085245374","https://openalex.org/W2103279870","https://openalex.org/W2109189270","https://openalex.org/W2158972663","https://openalex.org/W2166823384","https://openalex.org/W2399225924","https://openalex.org/W2400063444","https://openalex.org/W2404645331","https://openalex.org/W3159973907","https://openalex.org/W6608156246","https://openalex.org/W6712610176","https://openalex.org/W6713902026","https://openalex.org/W6794920904"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W3145575561","https://openalex.org/W2995886640","https://openalex.org/W1591475660","https://openalex.org/W2001275470","https://openalex.org/W2164162849"],"abstract_inverted_index":{"Most":[0],"HMM-based":[1],"TTS":[2],"systems":[3],"use":[4,144],"a":[5,11,25,108,145],"hard":[6,132],"voiced/unvoiced":[7,133,155],"classification":[8],"to":[9,143],"produce":[10,119],"discontinuous":[12],"F0":[13,47,147],"signal":[14,148],"which":[15],"is":[16,29,139],"used":[17],"for":[18,141],"the":[19,22,42,46,50,55,61,67,76,80,111,136,152,158],"generation":[20],"of":[21,40,45,63,79,85,113,131,157],"source-excitation.":[23],"When":[24],"mixed":[26,93],"source":[27],"excitation":[28],"used,":[30],"this":[31],"decision":[32,156],"can":[33],"be":[34],"based":[35],"on":[36,151],"two":[37],"different":[38],"sources":[39],"information:":[41],"state-specific":[43],"MSD-prior":[44],"models,":[48],"and/or":[49],"frame-specific":[51],"features":[52],"generated":[53,81],"by":[54],"aperiodicity":[56,159],"model.":[57,160],"This":[58,123],"paper":[59],"examines":[60],"meaning":[62],"these":[64],"variables":[65],"in":[66,110],"synthesis":[68,142],"process,":[69],"their":[70],"interaction,":[71],"and":[72,149],"how":[73],"they":[74],"affect":[75],"perceived":[77],"quality":[78],"speech":[82],"The":[83],"results":[84],"several":[86],"perceptual":[87,121],"experiments":[88],"show":[89],"that":[90,125],"when":[91],"using":[92,128],"excitation,":[94],"subjects":[95],"consistently":[96],"prefer":[97],"samples":[98],"with":[99],"very":[100],"few":[101],"or":[102],"no":[103],"false":[104,114],"unvoiced":[105],"errors,":[106],"whereas":[107],"reduction":[109],"rate":[112],"voiced":[115],"errors":[116],"does":[117],"not":[118],"any":[120,129],"improvement.":[122],"suggests":[124],"rather":[126],"than":[127],"form":[130],"classification,":[134],"e.g.,":[135],"MSD-prior,":[137],"it":[138],"better":[140],"continuous":[146],"rely":[150],"frame-level":[153],"soft":[154]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
