{"id":"https://openalex.org/W2406719960","doi":"https://doi.org/10.21437/interspeech.2014-191","title":"An iterative approach to decision tree training for context dependent speech synthesis","display_name":"An iterative approach to decision tree training for context dependent speech synthesis","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2406719960","doi":"https://doi.org/10.21437/interspeech.2014-191","mag":"2406719960"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-191","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5083694318","display_name":"Xiayu Chen","orcid":"https://orcid.org/0000-0002-2318-9921"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiayu Chen","raw_affiliation_strings":["***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["***University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21830542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2327","last_page":"2331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9757000207901001,"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":0.9757000207901001,"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/T12031","display_name":"Speech and dialogue systems","score":0.9023000001907349,"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/computer-science","display_name":"Computer science","score":0.7678859233856201},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.7075406908988953},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6234164834022522},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.600841760635376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47219786047935486},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4618896543979645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43385568261146545},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41032078862190247},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35840702056884766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12307193875312805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678859233856201},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.7075406908988953},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6234164834022522},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.600841760635376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47219786047935486},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4618896543979645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43385568261146545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41032078862190247},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35840702056884766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12307193875312805},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2014-191","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.707.6862","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.707.6862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://isle.illinois.edu/sst/pubs/2014/chen14interspeech.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"In":[0],"speech":[1,117,119],"synthesis":[2],"with":[3,70,86],"sparse":[4],"training":[5,23,75],"data,":[6],"phonetic":[7],"decision":[8,27,51,123],"trees":[9,28],"are":[10,29],"frequently":[11],"used":[12],"for":[13,33,77],"balance":[14],"between":[15],"model":[16,85],"complexity":[17],"and":[18,79,100],"avail-able":[19],"data.":[20],"The":[21,62,89],"traditional":[22],"procedure":[24,67,73],"is":[25,53,68,98],"that":[26,104],"constructed":[30],"after":[31,55],"parameters":[32,76],"each":[34],"phones":[35],"optimized":[36],"in":[37,48],"the":[38,50,59,65,71],"EM":[39,60,121],"al-gorithm.":[40],"This":[41],"paper":[42],"proposes":[43],"an":[44,83],"iterative":[45,105],"re-optimization":[46,106],"algorithm":[47],"which":[49],"tree":[52,124],"re-learned":[54],"every":[56],"iteration":[57],"of":[58,64],"algorithm.":[61],"performance":[63],"new":[66],"compared":[69],"original":[72],"by":[74],"MFCC":[78],"F0":[80],"features":[81],"using":[82],"EDHMM":[84],"data":[87],"from":[88],"Boston":[90],"Uni-versity":[91],"Radio":[92],"Speech":[93],"corpus.":[94],"A":[95],"convergence":[96],"proof":[97],"presented,":[99],"experimental":[101],"tests":[102],"demonstrate":[103],"gener-ates":[107],"statistically":[108],"significant":[109],"test":[110],"corpus":[111],"log-likelihood":[112],"improvements.":[113],"Index":[114],"Terms":[115],"\u2014":[116],"synthesis,":[118],"clustering,":[120],"algo-rithm,":[122],"1.":[125]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}