{"id":"https://openalex.org/W2605083903","doi":"https://doi.org/10.1145/3033288.3033329","title":"Acoustic Modeling for Lhasa Tibetan Speech Synthesis Based on DAEM Algorithm","display_name":"Acoustic Modeling for Lhasa Tibetan Speech Synthesis Based on DAEM Algorithm","publication_year":2016,"publication_date":"2016-12-17","ids":{"openalex":"https://openalex.org/W2605083903","doi":"https://doi.org/10.1145/3033288.3033329","mag":"2605083903"},"language":"en","primary_location":{"id":"doi:10.1145/3033288.3033329","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3033288.3033329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth International Conference on Network, Communication and Computing","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/A5075111208","display_name":"Shipeng Xu","orcid":"https://orcid.org/0000-0003-0054-0157"},"institutions":[{"id":"https://openalex.org/I124644866","display_name":"Northwest Minzu University","ror":"https://ror.org/04cyy9943","country_code":"CN","type":"education","lineage":["https://openalex.org/I124644866"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shipeng Xu","raw_affiliation_strings":["Northwest University for Nationalities, Key Laboratory of National language intelligent processing, China"],"affiliations":[{"raw_affiliation_string":"Northwest University for Nationalities, Key Laboratory of National language intelligent processing, China","institution_ids":["https://openalex.org/I124644866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070824547","display_name":"Hongzhi Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I124644866","display_name":"Northwest Minzu University","ror":"https://ror.org/04cyy9943","country_code":"CN","type":"education","lineage":["https://openalex.org/I124644866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Yu","raw_affiliation_strings":["Northwest University for Nationalities, Key Laboratory of National language intelligent processing, China"],"affiliations":[{"raw_affiliation_string":"Northwest University for Nationalities, Key Laboratory of National language intelligent processing, China","institution_ids":["https://openalex.org/I124644866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101494512","display_name":"Guanyu Li","orcid":"https://orcid.org/0000-0002-9829-6131"},"institutions":[{"id":"https://openalex.org/I124644866","display_name":"Northwest Minzu University","ror":"https://ror.org/04cyy9943","country_code":"CN","type":"education","lineage":["https://openalex.org/I124644866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanyu Li","raw_affiliation_strings":["Northwest University for Nationalities, Key Laboratory of National language intelligent processing, China"],"affiliations":[{"raw_affiliation_string":"Northwest University for Nationalities, Key Laboratory of National language intelligent processing, China","institution_ids":["https://openalex.org/I124644866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101538449","display_name":"Hanbin Zhang","orcid":"https://orcid.org/0000-0002-8893-4208"},"institutions":[{"id":"https://openalex.org/I124644866","display_name":"Northwest Minzu University","ror":"https://ror.org/04cyy9943","country_code":"CN","type":"education","lineage":["https://openalex.org/I124644866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanbin Zhang","raw_affiliation_strings":["Northwest University for Nationalities, Key Laboratory of National language intelligent processing, China"],"affiliations":[{"raw_affiliation_string":"Northwest University for Nationalities, Key Laboratory of National language intelligent processing, China","institution_ids":["https://openalex.org/I124644866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100643103","display_name":"Jun Ma","orcid":"https://orcid.org/0009-0003-8713-0667"},"institutions":[{"id":"https://openalex.org/I124644866","display_name":"Northwest Minzu University","ror":"https://ror.org/04cyy9943","country_code":"CN","type":"education","lineage":["https://openalex.org/I124644866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["Northwest University for Nationalities, Key Laboratory of National language intelligent processing, China"],"affiliations":[{"raw_affiliation_string":"Northwest University for Nationalities, Key Laboratory of National language intelligent processing, China","institution_ids":["https://openalex.org/I124644866"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5075111208"],"corresponding_institution_ids":["https://openalex.org/I124644866"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12601843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"188","last_page":"192"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9908000230789185,"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/T11309","display_name":"Music and Audio Processing","score":0.9722999930381775,"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/computer-science","display_name":"Computer science","score":0.7270354628562927},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7199869155883789},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7178963422775269},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6931255459785461},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6421940922737122},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5237712264060974},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4669794738292694},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40933656692504883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3930487036705017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7270354628562927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7199869155883789},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7178963422775269},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6931255459785461},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6421940922737122},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5237712264060974},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4669794738292694},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40933656692504883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3930487036705017},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3033288.3033329","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3033288.3033329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifth International Conference on Network, Communication and Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1976374954","https://openalex.org/W1979449467","https://openalex.org/W1981618467","https://openalex.org/W2000513720","https://openalex.org/W2007463795","https://openalex.org/W2042600255","https://openalex.org/W2098651640","https://openalex.org/W2101133792","https://openalex.org/W2111284386","https://openalex.org/W2116082100","https://openalex.org/W2129142580","https://openalex.org/W2130257620","https://openalex.org/W2366727955","https://openalex.org/W2380370523"],"related_works":["https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2121652828","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055"],"abstract_inverted_index":{"This":[0],"paper":[1],"applies":[2],"the":[3,34,42,59,64,71,74,79,94,103,112,115,120,126],"deterministic":[4],"annealing":[5],"expectation":[6],"maximum":[7,46],"(DAEM)":[8],"algorithm":[9,32,50,122],"into":[10],"HMM-based":[11],"Lhasa":[12,22,96,144],"Tibetan":[13,23,97,117,145],"speech":[14,24,29,85,98,105,109,118,146,152],"synthesis.":[15],"In":[16,58],"this":[17,56,67],"way,":[18],"we":[19],"can":[20,40,69,136],"synthesize":[21],"with":[25,102,106,148],"non-time":[26,149],"labeled":[27,108,150],"training":[28,129,140,151],"corpus.":[30,110,153],"EM":[31],"has":[33,51,99],"problem":[35,43],"of":[36,44,83,114,128,143],"initialization":[37],"dependence,":[38],"which":[39],"cause":[41],"local":[45],"values.":[47],"The":[48],"DAEM":[49,121],"been":[52],"introduced":[53],"to":[54,77],"solve":[55],"problem.":[57],"process":[60],"embedded":[61],"re-evaluation":[62],"during":[63],"model":[65],"training,":[66],"method":[68,135],"make":[70],"computer":[72],"obtain":[73],"optimal":[75],"parameters":[76],"determine":[78],"best":[80],"time":[81,107],"boundary":[82],"each":[84],"synthesis":[86,147],"unit.":[87],"Objective":[88],"and":[89],"subjective":[90],"evaluation":[91],"show":[92],"that":[93],"synthesized":[95,104,116],"similar":[100],"quality":[101],"Especially,":[111],"MOS":[113],"by":[119],"is":[123,131],"higher":[124],"when":[125],"number":[127],"sentences":[130],"700.":[132],"Therefore,":[133],"proposed":[134],"be":[137],"used":[138],"for":[139],"acoustic":[141],"models":[142]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
