{"id":"https://openalex.org/W2163246542","doi":"https://doi.org/10.1109/icassp.2008.4518519","title":"Minumum generation error linear regression based model adaptation for HMM-based speech synthesis","display_name":"Minumum generation error linear regression based model adaptation for HMM-based speech synthesis","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2163246542","doi":"https://doi.org/10.1109/icassp.2008.4518519","mag":"2163246542"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518519","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/A5064290493","display_name":"Long Qin","orcid":"https://orcid.org/0000-0001-5639-4983"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Long Qin","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology, China","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology, China","institution_ids":[]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039492028","display_name":"Yi-Jian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi-Jian Wu","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069176378","display_name":"Zhen-Hua Ling","orcid":null},"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":["University of Science and Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045299550","display_name":"Ren-Hua Wang","orcid":null},"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":"Ren-Hua Wang","raw_affiliation_strings":["University of Science and Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110935514","display_name":"Lirong Dai","orcid":null},"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":["University of Science and Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7743,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.70445523,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"5","issue":null,"first_page":"3953","last_page":"3956"},"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":0.9912999868392944,"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":0.9857000112533569,"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":0.760650634765625},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7470656633377075},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7175664901733398},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6392971873283386},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.633014440536499},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.5147221684455872},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.48849713802337646},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.45630401372909546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4350472092628479},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42141228914260864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22794145345687866},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14484485983848572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1369200050830841}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.760650634765625},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7470656633377075},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175664901733398},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6392971873283386},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.633014440536499},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.5147221684455872},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.48849713802337646},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.45630401372909546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4350472092628479},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42141228914260864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22794145345687866},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14484485983848572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1369200050830841},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518519","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W128185859","https://openalex.org/W129217914","https://openalex.org/W284180566","https://openalex.org/W330074099","https://openalex.org/W1600722501","https://openalex.org/W1935012542","https://openalex.org/W1993523973","https://openalex.org/W2010581677","https://openalex.org/W2049686551","https://openalex.org/W2111194146","https://openalex.org/W2146871184","https://openalex.org/W2160084280","https://openalex.org/W3036802551","https://openalex.org/W6605245121","https://openalex.org/W6610316872","https://openalex.org/W6676358011","https://openalex.org/W6780476513","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2610868774","https://openalex.org/W4399767649","https://openalex.org/W2092994918","https://openalex.org/W3216594821","https://openalex.org/W2390006526","https://openalex.org/W31220157","https://openalex.org/W1915333409","https://openalex.org/W2393341384"],"abstract_inverted_index":{"Due":[0],"to":[1,34,39,62,66,71],"the":[2,5,12,36,58,73,77,83,93,106,112,118,122,125,128,136],"inconsistency":[3],"between":[4],"maximum":[6,94],"likelihood":[7,95],"(ML)":[8],"based":[9,53,99],"training":[10],"and":[11,124],"synthesis":[13],"application":[14],"in":[15],"HMM-based":[16,43],"speech":[17,44,79,130],"synthesis,":[18],"a":[19,48],"minimum":[20],"generation":[21,74,107],"error":[22],"(MGE)":[23],"criterion":[24,38],"had":[25],"been":[26],"proposed":[27,87],"for":[28,42,76],"HMM":[29],"training.":[30],"This":[31],"paper":[32],"continues":[33],"apply":[35],"MGE":[37,49],"model":[40,54,100,114],"adaptation":[41,55],"synthesis.":[45],"We":[46],"propose":[47],"linear":[50,96],"regression":[51,59,97],"(MGELR)":[52],"algorithm,":[56],"where":[57],"matrices":[60],"used":[61],"transform":[63],"source":[64],"models":[65,68],"target":[67,84],"are":[69],"optimized":[70],"minimize":[72],"errors":[75,108],"input":[78],"data":[80],"uttered":[81],"by":[82],"speaker.":[85],"The":[86],"MGELR":[88,132],"approach":[89],"was":[90],"compared":[91],"with":[92],"(MLLR)":[98],"adaptation.":[101,115],"Experimental":[102],"results":[103,137],"indicate":[104],"that":[105],"were":[109,133],"reduced":[110],"after":[111],"MGELR-based":[113],"And":[116],"from":[117],"subjective":[119],"listening":[120],"test,":[121],"discrimination":[123],"quality":[126],"of":[127],"synthesized":[129],"using":[131,138],"better":[134],"than":[135],"MLLR.":[139]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}