{"id":"https://openalex.org/W2146821381","doi":"https://doi.org/10.1109/sped.2011.5940735","title":"Sources of increased variability in HMM synthetic voices","display_name":"Sources of increased variability in HMM synthetic voices","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2146821381","doi":"https://doi.org/10.1109/sped.2011.5940735","mag":"2146821381"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2011.5940735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2011.5940735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 6th Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5038640628","display_name":"Marius Cotescu","orcid":"https://orcid.org/0000-0001-7005-2920"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Marius Cotescu","raw_affiliation_strings":["Applied Electronics and Information Engineering Department, University Politehnica of Bucharest, Bucharest, Romania","Applied Electronics and Information Eng. Dept University Politehnica of Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"Applied Electronics and Information Engineering Department, University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"Applied Electronics and Information Eng. Dept University Politehnica of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006081117","display_name":"Inge Gav\u0103t","orcid":null},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Inge Gavat","raw_affiliation_strings":["Applied Electronics and Information Engineering Department, University Politehnica of Bucharest, Bucharest, Romania","Applied Electronics and Information Eng. Dept University Politehnica of Bucharest, Romania"],"affiliations":[{"raw_affiliation_string":"Applied Electronics and Information Engineering Department, University Politehnica of Bucharest, Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]},{"raw_affiliation_string":"Applied Electronics and Information Eng. Dept University Politehnica of Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038640628"],"corresponding_institution_ids":["https://openalex.org/I61641377"],"apc_list":null,"apc_paid":null,"fwci":0.4276,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.7392622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9977999925613403,"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/vocal-tract","display_name":"Vocal tract","score":0.82468581199646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6755977869033813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6205347180366516},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5765417218208313},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5586338639259338},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5385796427726746},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5123839974403381},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5022828578948975},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.47907572984695435},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4602033793926239},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.42768967151641846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3845791816711426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20911049842834473},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.1689395308494568},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1323610246181488}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.82468581199646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6755977869033813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6205347180366516},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5765417218208313},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5586338639259338},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5385796427726746},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5123839974403381},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5022828578948975},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.47907572984695435},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4602033793926239},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.42768967151641846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3845791816711426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20911049842834473},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.1689395308494568},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1323610246181488}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped.2011.5940735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2011.5940735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 6th Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322509","display_name":"Kungliga Tekniska H\u00f6gskolan","ror":"https://ror.org/026vcq606"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W35971819","https://openalex.org/W217960407","https://openalex.org/W1499550022","https://openalex.org/W1512429158","https://openalex.org/W1570629387","https://openalex.org/W2010744927","https://openalex.org/W2049686551","https://openalex.org/W2074854222","https://openalex.org/W2154920538","https://openalex.org/W2296704011","https://openalex.org/W2395578248","https://openalex.org/W2406017614","https://openalex.org/W3177989406","https://openalex.org/W4245838404","https://openalex.org/W6601469065","https://openalex.org/W6608789936","https://openalex.org/W6630838124","https://openalex.org/W6697285287","https://openalex.org/W6711777497","https://openalex.org/W6714191056","https://openalex.org/W6798679566","https://openalex.org/W7010239571"],"related_works":["https://openalex.org/W2100012411","https://openalex.org/W1482212662","https://openalex.org/W3162157266","https://openalex.org/W2162084437","https://openalex.org/W1997579527","https://openalex.org/W3044927199","https://openalex.org/W2102353451","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097"],"abstract_inverted_index":{"The":[0,62,99],"paper":[1],"presents":[2],"a":[3,57],"study":[4],"on":[5,23],"the":[6,13,20,24,39,43,47,66,72,80,91,96],"effect":[7,63],"of":[8,11,19,26,46,64],"different":[9,33],"methods":[10],"coding":[12,34,45],"STRAIGHT":[14],"aperiodicity":[15],"coefficients":[16],"and":[17,56,68,75],"models":[18],"vocal":[21,81],"tract":[22,82],"quality":[25],"synthetic":[27,100],"speech":[28,73],"generated":[29],"using":[30,90],"HMMs.":[31],"Three":[32],"schemes":[35],"were":[36,88,102],"implemented":[37],"in":[38,50,104],"HTS":[40],"synthesis":[41],"system:":[42],"classic":[44],"mean":[48],"value":[49],"five":[51],"frequency":[52],"sub-bands,":[53],"Mel-cepstral":[54],"coefficients,":[55],"simple":[58],"unit":[59],"selection":[60],"method.":[61],"removing":[65],"energy":[67],"spectral":[69],"tilt":[70],"from":[71,79],"spectrum,":[74],"modeling":[76],"them":[77],"independently":[78],"was":[83],"also":[84],"studied.":[85],"Five":[86],"systems":[87],"trained":[89],"ARCTIC_SLT":[92],"database":[93],"to":[94],"test":[95],"proposed":[97],"methods.":[98],"voices":[101],"evaluated":[103],"three":[105],"subjective":[106],"listening":[107],"tests.":[108]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}