{"id":"https://openalex.org/W1985587198","doi":"https://doi.org/10.1109/icassp.2010.5495168","title":"Kalman tracking linear predictor for vowel intelligibility enhancement on european portuguese HMM based speech synthesis","display_name":"Kalman tracking linear predictor for vowel intelligibility enhancement on european portuguese HMM based speech synthesis","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1985587198","doi":"https://doi.org/10.1109/icassp.2010.5495168","mag":"1985587198"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/A5085729646","display_name":"Lu\u00eds Coelho","orcid":"https://orcid.org/0000-0002-5673-7306"},"institutions":[{"id":"https://openalex.org/I83863532","display_name":"Polytechnic Institute of Porto","ror":"https://ror.org/04988re48","country_code":"PT","type":"education","lineage":["https://openalex.org/I83863532"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Luis Coelho","raw_affiliation_strings":["Polytechnic Institute of Porto, ESEIG, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic Institute of Porto, ESEIG, Portugal","institution_ids":["https://openalex.org/I83863532"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108616325","display_name":"Daniela Braga","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092974","display_name":"Microsoft (Portugal)","ror":"https://ror.org/00eqfbw40","country_code":"PT","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210092974"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Daniela Braga","raw_affiliation_strings":["Microsoft Language Development Center, Microsoft Corporation, Lisboa, Portugal","Microsoft Corporation, Microsoft Language Development Center, Lisbon, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Language Development Center, Microsoft Corporation, Lisboa, Portugal","institution_ids":["https://openalex.org/I4210092974"]},{"raw_affiliation_string":"Microsoft Corporation, Microsoft Language Development Center, Lisbon, Portugal","institution_ids":["https://openalex.org/I4210092974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026717063","display_name":"Carm\u00e9n Garc\u00eda Mateo","orcid":"https://orcid.org/0000-0001-6856-939X"},"institutions":[{"id":"https://openalex.org/I6289922","display_name":"Universidade de Vigo","ror":"https://ror.org/05rdf8595","country_code":"ES","type":"education","lineage":["https://openalex.org/I6289922"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carmen Garcia-Mateo","raw_affiliation_strings":["Signal and Communications Theory Department, University of Vigo, Spain","University of Vigo, Signal and Communications Theory Department, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal and Communications Theory Department, University of Vigo, Spain","institution_ids":["https://openalex.org/I6289922"]},{"raw_affiliation_string":"University of Vigo, Signal and Communications Theory Department, Spain","institution_ids":["https://openalex.org/I6289922"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3201,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43084693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"4734","last_page":"4737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.9983000159263611,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7302994132041931},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7290477156639099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7180954217910767},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.652669370174408},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.6245330572128296},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.585281491279602},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5742684006690979},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.483994722366333},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.471056193113327},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4527077078819275},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43318304419517517},{"id":"https://openalex.org/keywords/brazilian-portuguese","display_name":"Brazilian Portuguese","score":0.42408472299575806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4183429777622223},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1970716118812561},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16898119449615479},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13108578324317932},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.09573861956596375},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09241986274719238}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7302994132041931},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7290477156639099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7180954217910767},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.652669370174408},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.6245330572128296},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.585281491279602},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5742684006690979},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.483994722366333},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.471056193113327},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4527077078819275},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43318304419517517},{"id":"https://openalex.org/C2778880076","wikidata":"https://www.wikidata.org/wiki/Q750553","display_name":"Brazilian Portuguese","level":3,"score":0.42408472299575806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4183429777622223},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1970716118812561},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16898119449615479},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13108578324317932},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.09573861956596375},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09241986274719238},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:recipp.ipp.pt:10400.22/7636","is_oa":false,"landing_page_url":"http://hdl.handle.net/10400.22/7636","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":null,"raw_type":"conference object"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W22889032","https://openalex.org/W222076935","https://openalex.org/W2046022441","https://openalex.org/W2051630343","https://openalex.org/W2084609288","https://openalex.org/W6608730375"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W4252942110","https://openalex.org/W1604114751","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W2549308614","https://openalex.org/W2023694213","https://openalex.org/W4377694462","https://openalex.org/W2958354987"],"abstract_inverted_index":{"The":[0,73,94],"recent":[1],"developments":[2],"on":[3,39],"Hidden":[4],"Markov":[5],"Models":[6],"(HMM)":[7],"based":[8,71],"speech":[9],"synthesis":[10],"showed":[11],"that":[12,61],"this":[13,51],"is":[14],"a":[15,31,55,63],"promising":[16],"technology":[17],"fully":[18],"capable":[19],"of":[20],"competing":[21],"with":[22],"other":[23],"established":[24],"techniques.":[25],"However":[26],"some":[27],"issues":[28],"still":[29],"lack":[30],"solution.":[32],"Several":[33],"authors":[34],"report":[35],"an":[36,79,84],"over-smoothing":[37],"phenomenon":[38],"both":[40],"time":[41,86],"and":[42,47,89,102,105],"frequencies":[43],"which":[44,82],"decreases":[45],"naturalness":[46],"sometimes":[48],"intelligibility.":[49],"In":[50],"work":[52],"we":[53],"present":[54],"new":[56],"vowel":[57],"intelligibility":[58],"enhancement":[59],"algorithm":[60],"uses":[62],"discrete":[64],"Kalman":[65],"filter":[66],"(DKF)":[67],"for":[68],"tracking":[69],"frame":[70,87],"parameters.":[72],"inter-frame":[74],"correlations":[75],"are":[76],"modelled":[77],"by":[78],"autoregressive":[80],"structure":[81],"provides":[83],"underlying":[85],"dependency":[88],"can":[90],"improve":[91],"time-frequency":[92],"resolution.":[93],"system's":[95],"performance":[96],"has":[97,109],"been":[98],"evaluated":[99],"using":[100],"objective":[101],"subjective":[103],"tests":[104],"the":[106],"proposed":[107],"methodology":[108],"led":[110],"to":[111],"improved":[112],"results.":[113]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}