{"id":"https://openalex.org/W2065795093","doi":"https://doi.org/10.1109/iscslp.2014.6936612","title":"Integrating global variance of log power spectrum derived from LSPs into MGE training for HMM-based parametric speech synthesis","display_name":"Integrating global variance of log power spectrum derived from LSPs into MGE training for HMM-based parametric speech synthesis","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2065795093","doi":"https://doi.org/10.1109/iscslp.2014.6936612","mag":"2065795093"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language 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/A5090652608","display_name":"Yusheng Sun","orcid":"https://orcid.org/0000-0002-7259-1407"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Sheng Sun","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101874107","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0003-0741-4831"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0979368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"5","issue":null,"first_page":"201","last_page":"205"},"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":0.9990000128746033,"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":0.9930999875068665,"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/naturalness","display_name":"Naturalness","score":0.8547106981277466},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8358960151672363},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7091171145439148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6982324123382568},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6488779783248901},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6003794074058533},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.47891247272491455},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4157373905181885},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3564552068710327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34788191318511963},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22439637780189514},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11535954475402832}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8547106981277466},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8358960151672363},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7091171145439148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6982324123382568},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6488779783248901},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6003794074058533},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.47891247272491455},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4157373905181885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3564552068710327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34788191318511963},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22439637780189514},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11535954475402832},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W157817982","https://openalex.org/W1514737389","https://openalex.org/W1600722501","https://openalex.org/W1935012542","https://openalex.org/W1963627370","https://openalex.org/W2000513720","https://openalex.org/W2009674825","https://openalex.org/W2010581677","https://openalex.org/W2049686551","https://openalex.org/W2111194146","https://openalex.org/W2144139079","https://openalex.org/W2156453709","https://openalex.org/W2159528802","https://openalex.org/W2376932199","https://openalex.org/W2401438872","https://openalex.org/W3036802551","https://openalex.org/W6676358011","https://openalex.org/W6682822505","https://openalex.org/W6683640347","https://openalex.org/W7056901721","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250","https://openalex.org/W2024201202","https://openalex.org/W2049083033"],"abstract_inverted_index":{"This":[0,59],"paper":[1],"presents":[2],"a":[3,91],"method":[4,55,60,92,130],"to":[5,40,93,111],"improve":[6],"hidden":[7],"Markov":[8],"model":[9,36,107,142],"(HMM)":[10],"based":[11,52],"parametric":[12],"speech":[13,66,137],"synthesis":[14,83,121,149],"by":[15],"integrating":[16],"global":[17],"variance":[18],"(GV)":[19],"of":[20,45,64,79,97,105,119,135,146],"log":[21],"power":[22],"spectrum":[23],"(LPS)":[24],"derived":[25,99],"from":[26,100],"line":[27],"spectral":[28,48,72,156],"pairs":[29],"(LSPs)":[30],"into":[31,102],"minimum":[32],"generation":[33,54,81],"error":[34],"(MGE)":[35],"training.":[37],"In":[38,86],"order":[39,110],"alleviate":[41],"the":[42,46,62,77,95,103,139],"over-smoothing":[43],"effect":[44],"generated":[47],"structures,":[49],"an":[50],"LPS-GV":[51,98],"parameter":[53,80],"has":[56],"been":[57],"proposed.":[58],"improved":[61],"naturalness":[63,134],"synthetic":[65,136],"when":[67,151],"LSPs":[68,101,152],"were":[69],"used":[70,154],"as":[71,155],"features.":[73,157],"However,":[74],"it":[75],"increased":[76],"complexity":[78],"at":[82,115,120,148],"time":[84,117,150],"significantly.":[85],"this":[87,128],"paper,":[88],"we":[89],"propose":[90],"integrate":[94],"distortions":[96],"criterion":[104],"MGE":[106,141],"training":[108,116,143],"in":[109],"utilize":[112],"LPSGV":[113],"information":[114],"instead":[118],"time.":[122],"The":[123],"experimental":[124],"results":[125],"show":[126],"that":[127],"proposed":[129],"can":[131],"achieve":[132],"better":[133],"than":[138],"conventional":[140],"without":[144],"loss":[145],"efficiency":[147],"are":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}