{"id":"https://openalex.org/W2146071708","doi":"https://doi.org/10.1109/icassp.2004.1326064","title":"Minimum segmentation error based discriminative training for speech synthesis application","display_name":"Minimum segmentation error based discriminative training for speech synthesis application","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2146071708","doi":"https://doi.org/10.1109/icassp.2004.1326064","mag":"2146071708"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 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/A5039492028","display_name":"Yi-Jian Wu","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":"Yi-Jian Wu","raw_affiliation_strings":["Spoken Language Translation Laboratories, ATR, Japan","University of Science and Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Translation Laboratories, ATR, Japan","institution_ids":[]},{"raw_affiliation_string":"University of Science and Technology, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["Spoken Language Translation Laboratories, ATR, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Translation Laboratories, ATR, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100888269","display_name":"Jinfu Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinfu Ni","raw_affiliation_strings":["Spoken Language Translation Laboratories, ATR, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Translation Laboratories, ATR, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102734836","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, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.134706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"629"},"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":0.9983999729156494,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/discriminative-model","display_name":"Discriminative model","score":0.8433302640914917},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.810570478439331},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7473012804985046},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7420899868011475},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6475261449813843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6431632041931152},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5068615078926086},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.46962669491767883},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.45288586616516113},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3733629584312439}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8433302640914917},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.810570478439331},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7473012804985046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7420899868011475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6475261449813843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6431632041931152},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5068615078926086},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.46962669491767883},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.45288586616516113},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3733629584312439}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W168484277","https://openalex.org/W1550350313","https://openalex.org/W1594082249","https://openalex.org/W1979761486","https://openalex.org/W2085684370","https://openalex.org/W2115678687","https://openalex.org/W2158289097","https://openalex.org/W6606916877","https://openalex.org/W6633029793","https://openalex.org/W6635743447"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W4313052709","https://openalex.org/W2945274617","https://openalex.org/W2022929107","https://openalex.org/W2055202857","https://openalex.org/W4205800335","https://openalex.org/W2758994127"],"abstract_inverted_index":{"In":[0,52,74],"the":[1,6,16,20,31,37,48,57,83,90,95,101,108,116,139],"conventional":[2],"HMM-based":[3],"segmentation":[4,17,68,84,102,119],"method,":[5,76],"HMM":[7,26,72,136],"training":[8,44,59],"is":[9,86,104,120,125,143],"based":[10],"on":[11,110,135],"MLE":[12],"criteria,":[13],"which":[14],"links":[15],"task":[18],"to":[19,29,35,82],"problem":[21],"of":[22,41,50,118,141],"distribution":[23],"estimation.":[24],"The":[25],"are":[27],"built":[28],"identify":[30],"phonetic":[32],"segments,":[33],"not":[34,131,144],"detect":[36],"boundary.":[38],"This":[39],"kind":[40],"inconsistency":[42],"between":[43],"and":[45,61,113],"application":[46],"limited":[47],"performance":[49],"segmentation.":[51],"this":[53,75,123],"paper,":[54],"we":[55,129],"adopt":[56],"discriminative":[58],"method":[60,124],"introduce":[62],"a":[63,77],"new":[64],"criterion,":[65],"named":[66],"minimum":[67],"error":[69,85,103],"(MSGE),":[70],"for":[71],"training.":[73],"loss":[78,93],"function":[79],"directly":[80],"related":[81],"defined.":[87],"By":[88],"minimizing":[89],"overall":[91],"empirical":[92],"with":[94],"generalized":[96],"probabilistic":[97],"descent":[98],"(GPD)":[99],"algorithm,":[100],"also":[105],"minimized.":[106],"From":[107],"results":[109],"both":[111],"Chinese":[112],"Japanese":[114],"data,":[115],"accuracy":[117],"improved.":[121],"Moreover,":[122],"robust":[126],"even":[127],"when":[128],"do":[130],"have":[132],"enough":[133],"knowledge":[134],"modeling,":[137],"e.g.":[138],"number":[140],"states":[142],"optimized.":[145]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}