{"id":"https://openalex.org/W2109247442","doi":"https://doi.org/10.21437/eurospeech.2003-662","title":"Probability models of formant parameters for voice conversion","display_name":"Probability models of formant parameters for voice conversion","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2109247442","doi":"https://doi.org/10.21437/eurospeech.2003-662","mag":"2109247442"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-662","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},"type":"article","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/A5001344814","display_name":"Dimitrios Rentzos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitrios Rentzos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109547430","display_name":"Saeed V. Vaseghi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saeed Vaseghi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064860911","display_name":"Yan Qin","orcid":"https://orcid.org/0000-0002-4184-9022"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110204490","display_name":"Ching-Hsiang Ho","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ching-Hsiang Ho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031047306","display_name":"Emir Turajli\u0107","orcid":"https://orcid.org/0000-0003-0274-660X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emir Turajlic","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4705,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.83158797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2405","last_page":"2408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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":0.9836999773979187,"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/formant","display_name":"Formant","score":0.9816594123840332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6591486930847168},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6123483777046204},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5387211441993713},{"id":"https://openalex.org/keywords/morphing","display_name":"Morphing","score":0.5367608666419983},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.508415162563324},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.49974846839904785},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.4552525281906128},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.44562235474586487},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4248775243759155},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35148105025291443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23448625206947327},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08924475312232971}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.9816594123840332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6591486930847168},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6123483777046204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5387211441993713},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.5367608666419983},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.508415162563324},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.49974846839904785},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.4552525281906128},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.44562235474586487},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4248775243759155},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35148105025291443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23448625206947327},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08924475312232971},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-662","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1526513105","https://openalex.org/W1594223010","https://openalex.org/W1704572586","https://openalex.org/W2000164896","https://openalex.org/W2156142001"],"related_works":["https://openalex.org/W1679315481","https://openalex.org/W3151495635","https://openalex.org/W4249408697","https://openalex.org/W2139081685","https://openalex.org/W1546995385","https://openalex.org/W2121622020","https://openalex.org/W4243357618","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,23,37,71,93,103,107,112,126,130,133,137],"estimation":[4],"and":[5,26,92,122],"mapping":[6,99,138],"of":[7,10,22,28,39,45,70,74,102,106,111,132,144],"probability":[8],"models":[9,57],"formant":[11,18,48,72,104,118],"parameter":[12,19],"vectors":[13,20,105],"for":[14,68,81,136],"voice":[15,82,145],"conversion.":[16],"The":[17,47,63,84],"consist":[21],"frequency,":[24],"bandwidth":[25],"intensity":[27],"resonance":[29],"at":[30],"formants.":[31],"Formant":[32],"parameters":[33,119],"are":[34,50,65,79,140],"derived":[35],"from":[36],"coefficients":[38],"a":[40,87],"linear":[41],"prediction":[42],"(LP)":[43],"model":[44],"speech.":[46,75],"distributions":[49],"modelled":[51],"with":[52,58],"phonemedependent":[53],"two-dimensional":[54],"hidden":[55],"Markov":[56],"state":[59],"Gaussian":[60],"mixture":[61],"densities.":[62],"HMMs":[64],"subsequently":[66],"used":[67],"re-estimation":[69],"trajectories":[73],"Two":[76],"alternative":[77],"methods":[78,115],"explored":[80],"morphing.":[83],"first":[85],"is":[86,95,148],"non-uniform":[88],"frequency":[89],"warping":[90,134],"method":[91],"second":[94],"based":[96],"on":[97],"spectral":[98],"via":[100],"rotation":[101],"source":[108],"towards":[109],"those":[110],"target.":[113],"Both":[114],"transform":[116],"all":[117],"(Frequency,":[120],"Bandwidth":[121],"Intensity).":[123],"In":[124],"addition,":[125],"factors":[127],"that":[128],"affect":[129],"selection":[131],"ratios":[135],"function":[139],"presented.":[141,149],"Experimental":[142],"evaluation":[143],"morphing":[146],"examples":[147]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}