{"id":"https://openalex.org/W2400337294","doi":"https://doi.org/10.21437/interspeech.2015-124","title":"Combining extreme learning machine and decision tree for duration prediction in HMM based speech synthesis","display_name":"Combining extreme learning machine and decision tree for duration prediction in HMM based speech synthesis","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2400337294","doi":"https://doi.org/10.21437/interspeech.2015-124","mag":"2400337294"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100322935","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0003-2500-5708"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["Institute of Automation. Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation. Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108361021","display_name":"Minghao Yang","orcid":"https://orcid.org/0000-0001-5397-3576"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghao Yang","raw_affiliation_strings":["Institute of Automation. Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation. Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Institute of Automation. Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation. Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Institute of Automation. Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation. Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2197","last_page":"2201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","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/T12676","display_name":"Machine Learning and ELM","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9625999927520752,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9610000252723694,"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":0.8947507739067078},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.8277784585952759},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.7680401802062988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7531198263168335},{"id":"https://openalex.org/keywords/extreme-learning-machine","display_name":"Extreme learning machine","score":0.6936543583869934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5876567959785461},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.562019944190979},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.556456983089447},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.509818971157074},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.47393518686294556},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4534880518913269},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4338008761405945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33269140124320984},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19540253281593323}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8947507739067078},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.8277784585952759},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.7680401802062988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531198263168335},{"id":"https://openalex.org/C2780150128","wikidata":"https://www.wikidata.org/wiki/Q21948731","display_name":"Extreme learning machine","level":3,"score":0.6936543583869934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5876567959785461},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.562019944190979},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.556456983089447},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.509818971157074},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47393518686294556},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4534880518913269},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4338008761405945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33269140124320984},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19540253281593323},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W133559434","https://openalex.org/W1486669519","https://openalex.org/W1512429158","https://openalex.org/W1993717606","https://openalex.org/W2004590799","https://openalex.org/W2014954256","https://openalex.org/W2025789483","https://openalex.org/W2064148454","https://openalex.org/W2068886129","https://openalex.org/W2078597717","https://openalex.org/W2106792148","https://openalex.org/W2109938215","https://openalex.org/W2111284386","https://openalex.org/W2121971770","https://openalex.org/W2147186888","https://openalex.org/W2154920538","https://openalex.org/W2376932199","https://openalex.org/W2400063444","https://openalex.org/W2915907762","https://openalex.org/W3144745230"],"related_works":["https://openalex.org/W2067443264","https://openalex.org/W31566076","https://openalex.org/W4297902562","https://openalex.org/W2741186499","https://openalex.org/W2804652951","https://openalex.org/W2556335056","https://openalex.org/W1986096622","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"Hidden":[0],"Markov":[1],"Model":[2],"(HMM)":[3],"based":[4],"speech":[5],"synthesis":[6],"using":[7],"Decision":[8],"Tree":[9],"(DT)":[10],"for":[11,50,64],"duration":[12,30,53,67],"prediction":[13,31],"is":[14],"known":[15],"to":[16],"produce":[17],"over-averaged":[18],"rhythm.":[19],"To":[20],"alleviate":[21],"this":[22,24,93],"problem,":[23],"paper":[25],"proposes":[26],"a":[27],"two":[28],"level":[29,52,66],"method":[32,38,74,94],"together":[33],"with":[34],"outlier":[35],"removal.":[36],"This":[37],"takes":[39],"advantages":[40],"of":[41,58,77,83],"accurate":[42],"regression":[43],"capability":[44,57],"by":[45,62],"Extreme":[46],"Learning":[47],"Machine":[48],"(ELM)":[49],"phone":[51,78],"prediction,":[54],"and":[55,86],"the":[56,73,81],"distributing":[59],"state":[60,65],"durations":[61],"DT":[63],"prediction.":[68],"Experimental":[69],"results":[70],"showed":[71],"that":[72],"decreased":[75],"RMSE":[76],"duration,":[79,85],"increased":[80],"fluctuation":[82],"syllable":[84],"achieved":[87],"63.75%":[88],"in":[89],"preference":[90],"evaluation.":[91],"Furthermore,":[92],"does":[95],"not":[96],"incur":[97],"laborious":[98],"manual":[99],"alignment":[100],"on":[101],"training":[102],"corpus.":[103]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}