{"id":"https://openalex.org/W2542179260","doi":"https://doi.org/10.1109/coginfocom.2012.6421934","title":"A novel codebook-based excitation model for use in speech synthesis","display_name":"A novel codebook-based excitation model for use in speech synthesis","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2542179260","doi":"https://doi.org/10.1109/coginfocom.2012.6421934","mag":"2542179260"},"language":"en","primary_location":{"id":"doi:10.1109/coginfocom.2012.6421934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2012.6421934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom)","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/A5016031960","display_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","orcid":"https://orcid.org/0000-0003-4375-7524"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Tamas Gabor Csapo","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069988513","display_name":"G\u00e9za N\u00e9meth","orcid":"https://orcid.org/0000-0002-2311-4858"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Geza Nemeth","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016031960"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":3.425,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.9305254,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"661","last_page":"665"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9980000257492065,"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":0.9962000250816345,"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/codebook","display_name":"Codebook","score":0.9587088823318481},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.7437148094177246},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7204602956771851},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7043746113777161},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.687746524810791},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5779504179954529},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.5352407693862915},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5351976156234741},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.44584691524505615},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4132160544395447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.385949045419693},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16770702600479126},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06707194447517395}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.9587088823318481},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.7437148094177246},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7204602956771851},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7043746113777161},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.687746524810791},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5779504179954529},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.5352407693862915},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5351976156234741},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.44584691524505615},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4132160544395447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.385949045419693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16770702600479126},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06707194447517395},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coginfocom.2012.6421934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2012.6421934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W181056519","https://openalex.org/W1499550022","https://openalex.org/W1971415293","https://openalex.org/W2016730668","https://openalex.org/W2066999516","https://openalex.org/W2074854222","https://openalex.org/W2097634052","https://openalex.org/W2107449214","https://openalex.org/W2150658333","https://openalex.org/W2286166914","https://openalex.org/W2295406225","https://openalex.org/W2404911693","https://openalex.org/W2408267635","https://openalex.org/W4293569503","https://openalex.org/W6676325967","https://openalex.org/W6696156092"],"related_works":["https://openalex.org/W2014919663","https://openalex.org/W4252671892","https://openalex.org/W193702574","https://openalex.org/W1842536210","https://openalex.org/W1967664370","https://openalex.org/W2155010696","https://openalex.org/W1979693044","https://openalex.org/W1999835922","https://openalex.org/W2063862874","https://openalex.org/W2154415461"],"abstract_inverted_index":{"Speech":[0],"synthesis":[1,17,74,128],"is":[2,22,33,55,66,78],"an":[3],"important":[4],"modality":[5],"in":[6,15,84,97,118],"Cognitive":[7],"Infocommunications.":[8],"Statistical":[9],"parametric":[10,126],"methods":[11],"have":[12],"gained":[13],"importance":[14],"speech":[16,20,36,42,53,104,127],"recently.":[18],"The":[19,31],"signal":[21,54],"decomposed":[23],"to":[24,105],"parameters":[25],"and":[26,58,88],"later":[27],"restored":[28],"from":[29,68],"them.":[30],"decomposition":[32],"implemented":[34],"by":[35],"coders.":[37],"We":[38],"propose":[39],"a":[40,59,81,106],"novel":[41],"coding":[43],"method":[44,101],"with":[45],"codebook-based":[46],"excitation.":[47],"In":[48],"the":[49,52,69,73,76,100,110,119,124],"analysis":[50],"stage":[51,75],"analyzed":[56],"frame-by-frame":[57],"codebook":[60,77],"of":[61,123],"phoneme-dependent,":[62],"pitch":[63],"synchronous":[64],"residuals":[65],"built":[67],"voiced":[70,86],"parts.":[71],"During":[72],"searched":[79],"for":[80],"suitable":[82],"element":[83],"each":[85],"frame":[87],"these":[89],"are":[90],"concatenated.":[91],"Our":[92],"initial":[93],"experiments":[94],"show":[95],"that":[96],"most":[98],"cases":[99],"can":[102],"resynthesize":[103],"similar":[107],"quality":[108],"than":[109],"original.":[111],"This":[112],"new":[113],"excitation":[114],"model":[115],"fits":[116],"well":[117],"machine":[120],"learning":[121],"part":[122],"statistical":[125],"framework.":[129],"<sup":[130],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[132]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}