{"id":"https://openalex.org/W2030501716","doi":"https://doi.org/10.1109/icassp.2013.6638995","title":"Training a supra-segmental parametric F0 model without interpolating F0","display_name":"Training a supra-segmental parametric F0 model without interpolating F0","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2030501716","doi":"https://doi.org/10.1109/icassp.2013.6638995","mag":"2030501716"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638995","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/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":["Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, 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":["Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, 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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kate Knill","raw_affiliation_strings":["Toshiba Research Europe Ltd, Cambridge, Cambridgeshire, GB","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge, Cambridgeshire, GB","institution_ids":["https://openalex.org/I1292669757"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK","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, Kawasaki, Japan","Corp. R&D Center, Toshiba, Kawasaki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Corporate Research & Development Center, Kawasaki, Japan","institution_ids":["https://openalex.org/I1292669757"]},{"raw_affiliation_string":"Corp. R&D Center, Toshiba, Kawasaki, 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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6880","last_page":"6884"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.6878637075424194},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6259334683418274},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5796402096748352},{"id":"https://openalex.org/keywords/parametrization","display_name":"Parametrization (atmospheric modeling)","score":0.5154091119766235},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4986882209777832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49100688099861145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4451074004173279},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.43130603432655334},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.426630437374115},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42273014783859253},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.4148308038711548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23805060982704163},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12960141897201538},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07406818866729736}],"concepts":[{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.6878637075424194},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6259334683418274},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5796402096748352},{"id":"https://openalex.org/C202887219","wikidata":"https://www.wikidata.org/wiki/Q3895221","display_name":"Parametrization (atmospheric modeling)","level":3,"score":0.5154091119766235},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4986882209777832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49100688099861145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4451074004173279},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43130603432655334},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.426630437374115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42273014783859253},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.4148308038711548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23805060982704163},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12960141897201538},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07406818866729736},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74902906","wikidata":"https://www.wikidata.org/wiki/Q1190858","display_name":"Radiative transfer","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6638995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638995","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"},{"id":"pmh:oai:generic.eprints.org:623204","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/623204/","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":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W113106864","https://openalex.org/W162393072","https://openalex.org/W186987961","https://openalex.org/W191556021","https://openalex.org/W1600722501","https://openalex.org/W1935012542","https://openalex.org/W1964420823","https://openalex.org/W2029434926","https://openalex.org/W2075665712","https://openalex.org/W2085245374","https://openalex.org/W2095723991","https://openalex.org/W2106421426","https://openalex.org/W2109701384","https://openalex.org/W2133035145","https://openalex.org/W2147868561","https://openalex.org/W2158504378","https://openalex.org/W2166823384","https://openalex.org/W2292984643","https://openalex.org/W2333836441","https://openalex.org/W2408220395","https://openalex.org/W3144745230","https://openalex.org/W6607864401","https://openalex.org/W6674546848","https://openalex.org/W6679574054","https://openalex.org/W6683488333","https://openalex.org/W6792747768","https://openalex.org/W7075637324"],"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/W1537411440","https://openalex.org/W2024201202"],"abstract_inverted_index":{"Combining":[0],"multiple":[1],"intonation":[2,26],"models":[3,27],"at":[4],"different":[5],"linguistic":[6],"levels":[7,30],"is":[8],"an":[9],"effective":[10],"way":[11],"to":[12,56,64],"improve":[13],"the":[14,17,25,37,41,60,74,78,81,90,100,134],"naturalness":[15],"of":[16,22,36,43,48,80],"predicted":[18],"F0.":[19,127],"In":[20],"many":[21,47],"these":[23,49],"approaches,":[24],"for":[28,92,109],"suprasegmental":[29],"are":[31,51],"based":[32,96,130],"on":[33,97,102,131],"a":[34,71,110,119,123],"parametrization":[35],"log-F0":[38],"contours":[39],"over":[40],"units":[42],"that":[44,76,88],"level.":[45],"However,":[46],"parametrisations":[50],"not":[52],"stable":[53],"when":[54],"applied":[55],"discontinuous":[57],"signals.":[58],"Therefore,":[59],"F0":[61],"signal":[62],"has":[63],"be":[65],"interpolated.":[66],"These":[67],"interpolated":[68,126],"values":[69],"introduce":[70],"distortion":[72],"in":[73,118],"coefficients":[75],"degrades":[77],"quality":[79],"model.":[82],"This":[83],"paper":[84],"proposes":[85],"two":[86],"methods":[87],"eliminate":[89],"need":[91],"such":[93],"interpolation,":[94],"one":[95],"regularization":[98,132],"and":[99],"other":[101],"factor":[103],"analysis.":[104],"Subjective":[105],"evaluations":[106],"show":[107],"that,":[108],"Discrete-cosine-transform":[111],"(DCT)":[112],"syllable-level":[113],"model,":[114],"both":[115],"approaches":[116],"result":[117],"significant":[120],"improvement":[121],"w.r.t.":[122],"baseline":[124],"using":[125],"The":[128],"approach":[129],"yields":[133],"best":[135],"results.":[136]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}