{"id":"https://openalex.org/W3162848039","doi":"https://doi.org/10.1109/kst51265.2021.9415759","title":"Pali Speech Synthesis using HMM","display_name":"Pali Speech Synthesis using HMM","publication_year":2021,"publication_date":"2021-01-21","ids":{"openalex":"https://openalex.org/W3162848039","doi":"https://doi.org/10.1109/kst51265.2021.9415759","mag":"3162848039"},"language":"en","primary_location":{"id":"doi:10.1109/kst51265.2021.9415759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst51265.2021.9415759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 13th International Conference on Knowledge and Smart Technology (KST)","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/A5053878473","display_name":"Kittikan Charoenrattana","orcid":null},"institutions":[{"id":"https://openalex.org/I179193067","display_name":"Khon Kaen University","ror":"https://ror.org/03cq4gr50","country_code":"TH","type":"education","lineage":["https://openalex.org/I179193067"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Kittikan Charoenrattana","raw_affiliation_strings":["Natural Language and Speech Processing Laboratory, Khon Kaen University, Faculty of Science, Khon Kaen, Thailand"],"affiliations":[{"raw_affiliation_string":"Natural Language and Speech Processing Laboratory, Khon Kaen University, Faculty of Science, Khon Kaen, Thailand","institution_ids":["https://openalex.org/I179193067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008878621","display_name":"Pusadee Seresangtakul","orcid":"https://orcid.org/0000-0001-7579-2485"},"institutions":[{"id":"https://openalex.org/I179193067","display_name":"Khon Kaen University","ror":"https://ror.org/03cq4gr50","country_code":"TH","type":"education","lineage":["https://openalex.org/I179193067"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Pusadee Seresangtakul","raw_affiliation_strings":["Natural Language and Speech Processing Laboratory, Khon Kaen University, Faculty of Science, Khon Kaen, Thailand"],"affiliations":[{"raw_affiliation_string":"Natural Language and Speech Processing Laboratory, Khon Kaen University, Faculty of Science, Khon Kaen, Thailand","institution_ids":["https://openalex.org/I179193067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053878473"],"corresponding_institution_ids":["https://openalex.org/I179193067"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61469736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"16","issue":null,"first_page":"165","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8089202642440796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7984366416931152},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7655524015426636},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7374656796455383},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.7010183334350586},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.662392258644104},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6487804055213928},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5262362360954285},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.46869659423828125},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4325488209724426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33581697940826416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20768669247627258},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08657556772232056},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08615273237228394},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05731794238090515}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8089202642440796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7984366416931152},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7655524015426636},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7374656796455383},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.7010183334350586},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.662392258644104},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6487804055213928},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5262362360954285},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.46869659423828125},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4325488209724426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33581697940826416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20768669247627258},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08657556772232056},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08615273237228394},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05731794238090515},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kst51265.2021.9415759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst51265.2021.9415759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 13th International Conference on Knowledge and Smart Technology (KST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1659186216","https://openalex.org/W2043003570","https://openalex.org/W2110108310","https://openalex.org/W2320914920","https://openalex.org/W2405183419","https://openalex.org/W2480687816","https://openalex.org/W2782684248","https://openalex.org/W2782856092","https://openalex.org/W2787298605","https://openalex.org/W3009619352","https://openalex.org/W4240349272"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2038801705","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W2024201202","https://openalex.org/W2535215250","https://openalex.org/W2049083033","https://openalex.org/W290673751"],"abstract_inverted_index":{"In":[0,88],"this":[1],"paper,":[2],"we":[3,20,91,124,179],"present":[4],"a":[5,85],"Pali":[6,23],"(Thai)":[7],"speech":[8,69,83,86,94,137],"synthesis":[9],"system":[10],"using":[11,49,84],"the":[12,18,31,50,59,72,89,97,107,118,121,134,163,181,185,189,203,206],"parametric":[13],"statistical":[14],"approach.":[15],"To":[16,55,116],"develop":[17],"system,":[19,123],"recorded":[21],"40":[22],"chants.":[24],"Data":[25],"were":[26,47,79,155,198],"extracted":[27],"and":[28,36,40,67,106,140,143,158,166,192,200,205],"represented":[29],"by":[30,42],"Mel":[32],"frequency":[33,38],"cepstral":[34,182,186],"coefficients":[35,187],"fundamental":[37],"(F0),":[39],"labeled":[41],"force":[43],"alignment.":[44],"These":[45],"parameters":[46,70,78],"modeled":[48,92],"hidden":[51],"Markov":[52],"model":[53,99,109],"(HMM).":[54],"generate":[56],"synthesized":[57,95,136,168,193],"speech,":[58],"input":[60],"text":[61],"was":[62],"converted":[63],"into":[64],"context-dependent":[65],"phonemes":[66],"generated":[68],"from":[71],"trained":[73],"HMM":[74],"model.":[75],"The":[76,146,195],"resulting":[77],"used":[80],"for":[81,162,202],"synthesizing":[82],"vocoder.":[87],"study,":[90],"two":[93,135],"models:":[96],"first":[98],"represents":[100,110],"tone":[101,111],"in":[102,112,130,150,177],"syllable":[103],"levels":[104,114],"(tone-syllable)":[105],"second":[108],"phoneme":[113],"(tone-phoneme).":[115],"evaluate":[117],"naturalness":[119,149],"of":[120,188],"proposed":[122],"asked":[125],"13":[126],"users":[127],"to":[128],"participate":[129],"listening":[131],"tests":[132],"comparing":[133],"models":[138],"(tone-syllable":[139],"tone-phoneme":[141,167,207],"models)":[142],"original":[144,190],"speech.":[145],"results,":[147],"expressing":[148],"mean":[151],"opinion":[152],"score":[153],"(MOS),":[154],"4.21,":[156],"3.25,":[157],"3.32":[159],"(from":[160],"5)":[161],"original,":[164],"tone-syllable,":[165],"speeches,":[169],"respectively.":[170,209],"We":[171],"also":[172],"conducted":[173],"an":[174],"objective":[175],"test":[176],"which":[178],"calculated":[180],"distance":[183],"between":[184],"speeches":[191],"speeches.":[194],"average":[196],"distances":[197],"3.67":[199],"3.60":[201],"tone-syllable":[204],"models,":[208]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}