{"id":"https://openalex.org/W2144266456","doi":"https://doi.org/10.1109/icassp.2008.4518690","title":"Incorporation of phrase intonation to context clustering for average voice models in HMM-based Thai speech synthesis","display_name":"Incorporation of phrase intonation to context clustering for average voice models in HMM-based Thai speech synthesis","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2144266456","doi":"https://doi.org/10.1109/icassp.2008.4518690","mag":"2144266456"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518690","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5001737533","display_name":"Suphattharachai Chomphan","orcid":"https://orcid.org/0000-0002-7417-288X"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Suphattharachai Chomphan","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022405100","display_name":"Takao Kobayashi","orcid":"https://orcid.org/0000-0003-0387-8030"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Kobayashi","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001737533"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.2473545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"e86 d","issue":null,"first_page":"4637","last_page":"4640"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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/speech-recognition","display_name":"Speech recognition","score":0.8065236806869507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7794333100318909},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6444375514984131},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6268857717514038},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6018113493919373},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5798839330673218},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5750865936279297},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.5202559232711792},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.46146896481513977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44275084137916565},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4234657287597656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35869720578193665},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10872098803520203},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.058924853801727295}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8065236806869507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794333100318909},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6444375514984131},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6268857717514038},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6018113493919373},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5798839330673218},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5750865936279297},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.5202559232711792},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.46146896481513977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44275084137916565},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4234657287597656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35869720578193665},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10872098803520203},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.058924853801727295},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2008.4518690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518690","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50057757","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100572382","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326788","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W12391643","https://openalex.org/W60443401","https://openalex.org/W91067745","https://openalex.org/W1599512239","https://openalex.org/W1872605741","https://openalex.org/W2121399170","https://openalex.org/W2144139079","https://openalex.org/W2150258981","https://openalex.org/W2402756081","https://openalex.org/W6600532773"],"related_works":["https://openalex.org/W2535580602","https://openalex.org/W2081919107","https://openalex.org/W1607387412","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2150511655","https://openalex.org/W2535215250","https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W2811496854"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,12,42,46,53],"novel":[4],"approach":[5],"to":[6],"the":[7,22,26,31,63,72,86,96,100],"context":[8,64],"clustering":[9,65],"process":[10,66],"in":[11,62,83],"speaker":[13,32],"independent":[14],"HMM-based":[15],"Thai":[16],"speech":[17,102],"synthesis":[18],"for":[19],"improvement":[20],"of":[21,25,37,49,67,76,85,88,99],"tone":[23,89,97],"intelligibility":[24,87],"average":[27,78],"voice":[28,79,82],"and":[29,52,59,80],"also":[30],"adapted":[33,81],"voice.":[34],"A":[35],"couple":[36],"phrase":[38,54],"intonation":[39],"features":[40],"from":[41],"generative":[43],"model":[44],"including":[45],"baseline":[47],"value":[48],"fundamental":[50],"frequency":[51],"command":[55],"amplitude":[56],"are":[57,90],"extracted":[58],"thereafter":[60],"exploited":[61],"HMM":[68],"training":[69],"stage.":[70],"In":[71],"experiments,":[73],"subjective":[74],"evaluations":[75],"both":[77],"terms":[84],"conducted.":[91],"The":[92],"results":[93],"show":[94],"that":[95],"correctness":[98],"synthesized":[101],"is":[103],"significantly":[104],"improved.":[105]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}