{"id":"https://openalex.org/W1975096742","doi":"https://doi.org/10.1109/iscslp.2012.6423459","title":"Cross validation and Minimum Generation Error for improved model clustering in HMM-based TTS","display_name":"Cross validation and Minimum Generation Error for improved model clustering in HMM-based TTS","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1975096742","doi":"https://doi.org/10.1109/iscslp.2012.6423459","mag":"1975096742"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th 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/A5101692260","display_name":"Fenglong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng-Long Xie","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039492028","display_name":"Yi-Jian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-Jian Wu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4423,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71047925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"60","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9814000129699707,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9104999899864197,"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":0.8503893613815308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7431885600090027},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7184979319572449},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7013099193572998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5382115244865417},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5143995881080627},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4904420077800751},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48086363077163696},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4474737346172333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4414331316947937},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41449376940727234},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15521660447120667}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8503893613815308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7431885600090027},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7184979319572449},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7013099193572998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5382115244865417},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5143995881080627},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4904420077800751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48086363077163696},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4474737346172333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4414331316947937},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41449376940727234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15521660447120667},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2012.6423459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W102093577","https://openalex.org/W128185859","https://openalex.org/W344150399","https://openalex.org/W1512429158","https://openalex.org/W1981552604","https://openalex.org/W2038983046","https://openalex.org/W2111194146","https://openalex.org/W2131650634","https://openalex.org/W2154920538","https://openalex.org/W3104887532","https://openalex.org/W6604170644","https://openalex.org/W6605245121","https://openalex.org/W6611766843","https://openalex.org/W6630838124","https://openalex.org/W6676358011"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W1591475660","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W3145575561","https://openalex.org/W2164162849"],"abstract_inverted_index":{"In":[0,93],"HMM-based":[1],"speech":[2],"synthesis,":[3],"context-dependent":[4],"hidden":[5],"Markov":[6],"model":[7],"(HMM)":[8],"is":[9,32,65],"widely":[10],"used":[11],"for":[12],"its":[13],"capability":[14,57],"to":[15,24,38,76,99,118],"synthesize":[16],"highly":[17,66],"intelligible":[18],"and":[19,55,74,86],"fairly":[20],"smooth":[21],"speech.":[22],"However,":[23],"train":[25],"HMMs":[26],"of":[27,128],"all":[28],"possible":[29],"contexts":[30],"well":[31],"difficult,":[33],"or":[34],"even":[35],"impossible,":[36],"due":[37],"the":[39,77,82,116,129],"intrinsic,":[40],"insufficient":[41],"training":[42],"data":[43],"coverage":[44],"problem.":[45],"As":[46],"a":[47,105],"result,":[48],"thus":[49],"trained":[50],"models":[51],"may":[52],"over":[53],"fit":[54],"their":[56],"in":[58,63,90,121],"predicting":[59],"any":[60],"unseen":[61],"context":[62],"test":[64],"restricted.":[67],"Recently":[68],"cross-validation":[69],"(CV)":[70],"has":[71],"been":[72],"explored":[73],"applied":[75],"decision":[78,100],"tree-based":[79],"clustering":[80,102],"with":[81,104],"Maximum-Likelihood":[83],"(ML)":[84],"criterion":[85],"showed":[87],"improved":[88],"robustness":[89],"TTS":[91,123],"synthesis.":[92],"this":[94],"paper":[95],"we":[96],"generalize":[97],"CV":[98],"tree":[101],"but":[103],"different,":[106],"Minimum":[107],"Generation":[108],"Error":[109],"(MGE),":[110],"criterion.":[111],"Experimental":[112],"results":[113,120],"show":[114],"that":[115,127],"generalization":[117],"MGE":[119],"better":[122],"synthesis":[124],"performance":[125],"than":[126],"baseline":[130],"systems.":[131]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}