{"id":"https://openalex.org/W2106632010","doi":"https://doi.org/10.21437/interspeech.2009-150","title":"An improved minimum generation error based model adaptation for HMM-based speech synthesis","display_name":"An improved minimum generation error based model adaptation for HMM-based speech synthesis","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W2106632010","doi":"https://doi.org/10.21437/interspeech.2009-150","mag":"2106632010"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-150","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nitech.repo.nii.ac.jp/records/3456","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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 Inst. of Technol.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Inst. of Technol.#TAB#","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","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":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"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":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Inst. of Technol.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Inst. of Technol.#TAB#","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7311,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69408385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1787","last_page":"1790"},"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":0.9908999800682068,"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":0.9889000058174133,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7523316740989685},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7011861801147461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.699190616607666},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.6682640314102173},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6371043920516968},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6222629547119141},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5094721913337708},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45732441544532776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42914992570877075},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32684147357940674}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7523316740989685},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7011861801147461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.699190616607666},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.6682640314102173},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6371043920516968},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6222629547119141},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5094721913337708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45732441544532776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42914992570877075},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32684147357940674},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-150","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435323","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3456","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"INTERSPEECH 2009 10th Annual Conference of the International Speech Communication Association","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435323","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3456","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"INTERSPEECH 2009 10th Annual Conference of the International Speech Communication Association","raw_type":"conference paper"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W129217914","https://openalex.org/W233059834","https://openalex.org/W330074099","https://openalex.org/W1600722501","https://openalex.org/W1602430027","https://openalex.org/W2002342963","https://openalex.org/W2010581677","https://openalex.org/W2049686551","https://openalex.org/W2111194146","https://openalex.org/W2146871184","https://openalex.org/W2158942523","https://openalex.org/W2165856656","https://openalex.org/W2166823384","https://openalex.org/W3036802551"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"Aminimum":[0],"generation":[1,51],"error":[2],"(MGE)":[3],"criterion":[4,20,63,72],"had":[5],"been":[6],"proposedfor":[7],"model":[8,22,34,66],"training":[9],"in":[10],"HMM-based":[11],"speech":[12,25,111],"synthesis.":[13],"Inthis":[14],"paper,":[15],"we":[16,57],"apply":[17],"the":[18,50,59,87,90,99,105,118],"MGE":[19,30,71],"to":[21,41,48],"adaptation":[23,35],"forHMM-based":[24],"synthesis,":[26],"and":[27,73,98],"introduce":[28],"an":[29],"linear":[31],"regression(MGELR)":[32],"based":[33],"algorithm,":[36],"wherethe":[37],"regression":[38],"matrices":[39],"used":[40],"transform":[42],"source":[43],"models":[44],"are":[45],"optimizedso":[46],"as":[47],"minimize":[49],"errors":[52],"of":[53,80,109],"adaptationdata.":[54],"In":[55],"addition,":[56],"incorporate":[58],"recent":[60],"improvements":[61],"ofMGE":[62],"into":[64],"MGELR-based":[65],"adaptation,":[67],"includingstate":[68],"alignment":[69],"under":[70],"using":[74],"a":[75],"log":[76],"spectraldistortion":[77,84],"(LSD)":[78],"instead":[79],"Euclidean":[81],"distance":[82],"for":[83],"measure.":[85],"From":[86],"experimental":[88],"results,":[89],"adaptationperformance":[91],"was":[92],"improved":[93,116],"after":[94,112],"incorporating":[95],"these":[96],"twotechniques,":[97],"formal":[100],"listening":[101],"tests":[102],"showed":[103],"that":[104],"qualityand":[106],"speaker":[107],"similarity":[108],"synthesized":[110],"MGELRbasedadaptation":[113],"were":[114],"significantly":[115],"over":[117],"originalMLLR-based":[119],"adaptation.":[120]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}