{"id":"https://openalex.org/W86509243","doi":"https://doi.org/10.21437/interspeech.2010-180","title":"Excitation modeling based on waveform interpolation for HMM-based speech synthesis","display_name":"Excitation modeling based on waveform interpolation for HMM-based speech synthesis","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W86509243","doi":"https://doi.org/10.21437/interspeech.2010-180","mag":"86509243"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-180","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5110947099","display_name":"June Sig Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"June Sig Sung","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054169859","display_name":"Doo Hwa Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Doo Hwa Hong","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048720977","display_name":"Kyung Hwan Oh","orcid":"https://orcid.org/0000-0002-4232-2003"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyung Hwan Oh","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110947099"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":4.0594,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93528758,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"813","last_page":"816"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9962999820709229,"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":0.9592000246047974,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8902477025985718},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7757868766784668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6895269751548767},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.6785581111907959},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.594977617263794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5145744681358337},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5080924034118652},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.491629421710968},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4660068154335022},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39365360140800476}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8902477025985718},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7757868766784668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6895269751548767},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6785581111907959},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.594977617263794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5145744681358337},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5080924034118652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.491629421710968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4660068154335022},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39365360140800476},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"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:10.21437/interspeech.2010-180","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W6725010","https://openalex.org/W106974151","https://openalex.org/W129817288","https://openalex.org/W200094172","https://openalex.org/W1535285399","https://openalex.org/W2131025459","https://openalex.org/W2154920538","https://openalex.org/W2155498861","https://openalex.org/W2286166914","https://openalex.org/W2400063444"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W2176409448","https://openalex.org/W3040712279","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2039489009"],"abstract_inverted_index":{"It":[0],"is":[1,130,163],"generally":[2],"known":[3],"that":[4,340],"a":[5,23,74,107,125,141,154,172,176,218,246,254,272,329],"well-designed":[6],"excitation":[7,29,55,111,122,257,295],"produces":[8],"high":[9],"quality":[10,346],"signals":[11],"in":[12,253,303],"hidden":[13],"Markov":[14],"model":[15],"(HMM)-based":[16],"speech":[17,65,94,334],"synthesis":[18,66],"systems.":[19],"This":[20],"paper":[21],"proposes":[22],"novel":[24,108],"tech-":[25],"niques":[26],"for":[27,202],"generating":[28],"based":[30],"on":[31,333],"the":[32,53,63,70,79,114,121,158,185,204,211,224,232,237,263,279,283,287,294,298,307,311,320,325,341,345,348],"waveform":[33,115,128],"inter-":[34],"polation":[35],"(WI).":[36],"For":[37,119],"modeling":[38,56,112,302],"WI":[39,243,308],"parameters,":[40],"we":[41,105,147,220],"implemented":[42],"statistical":[43,182],"method":[44,81,289],"like":[45],"principal":[46,149],"component":[47,150],"analysis":[48,151],"(PCA).":[49],"The":[50,181,242,259],"parameters":[51,206],"of":[52,76,135,144,157,175,184,200,226,262,270,275,301,324,331,347],"proposed":[54,80,264,288],"techniques":[57],"can":[58,167,193,228],"be":[59,168,194,229],"easily":[60],"combined":[61],"with":[62],"conventional":[64,212],"sys-":[67],"tem":[68],"under":[69,113],"HMM":[71,213],"framework.":[72,118],"From":[73,328],"number":[75,330],"experi-":[77],"ments,":[78],"has":[82,337],"been":[83,338],"found":[84],"to":[85,110,153,222,236],"generate":[86],"more":[87,255],"naturally":[88],"sounding":[89],"speech.":[90,327,350],"Index":[91],"Terms:":[92],"HMM-based":[93],"synthesis,":[95,335],"Waveform":[96],"Inter-":[97],"polation,":[98],"Principal":[99],"Component":[100],"Analysis":[101],"In":[102],"this":[103],"paper,":[104],"propose":[106,342],"approach":[109,309],"interpolation":[116],"(WI)":[117],"parameterizing":[120],"generation":[123],"model,":[124],"charac-":[126],"teristic":[127],"(CW)":[129],"extracted":[131,159],"from":[132,231,297],"each":[133,145,165],"frame":[134],"LP":[136],"residual":[137],"signals.":[138],"To":[139],"derive":[140],"compact":[142],"representation":[143],"CW,":[146],"apply":[148],"(PCA)":[152],"collec-":[155],"tion":[156,313],"CW's.":[160],"Once":[161],"PCA":[162,178],"done,":[164],"CW":[166],"compactly":[169],"approximated":[170],"as":[171,278],"linear":[173,186],"combination":[174],"few":[177],"basis":[179],"vectors.":[180],"distribution":[183],"com-":[187],"bination":[188],"coefficients":[189],"and":[190,282],"their":[191],"dynamics":[192],"efficiently":[195],"de-":[196],"scribed":[197],"by":[198,209],"means":[199],"HMM's":[201,234],"which":[203,292,317],"relevant":[205],"are":[207,266],"estimated":[208],"following":[210],"training":[214],"pro-":[215],"cedure.":[216],"Given":[217],"sentence":[219],"want":[221],"synthesize,":[223],"sequence":[225],"CW's":[227,251],"generated":[230],"trained":[233],"according":[235],"maximum":[238],"likelihood":[239],"(ML)":[240],"criterion.":[241],"algorithm":[244],"enables":[245],"smooth":[247],"transition":[248],"between":[249],"adjacent":[250],"resulting":[252],"natural":[256],"signal.":[258],"major":[260],"advantages":[261],"technique":[265,343],"twofold.":[267],"First,":[268],"instead":[269],"using":[271],"fixed":[273],"set":[274],"waveforms":[276,296],"such":[277],"impulse":[280],"train":[281],"ran-":[284],"dom":[285],"noise,":[286],"finds":[290],"CWs":[291],"represents":[293],"various":[299],"kinds":[300],"frequency":[304],"domain.":[305],"Second,":[306],"lets":[310],"excita-":[312],"signal":[314],"evolve":[315],"smoothly,":[316],"may":[318],"reduce":[319],"audible":[321],"arti-":[322],"facts":[323],"synthesized":[326,349],"experiments":[332],"it":[336],"demonstrated":[339],"enhances":[344]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}