{"id":"https://openalex.org/W161540250","doi":"https://doi.org/10.21437/interspeech.2004-459","title":"Mutual-information based segment pre-selection in concatenative text-to-speech","display_name":"Mutual-information based segment pre-selection in concatenative text-to-speech","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W161540250","doi":"https://doi.org/10.21437/interspeech.2004-459","mag":"161540250"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-459","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5053942348","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0003-3694-2246"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109995018","display_name":"Ling Jin","orcid":"https://orcid.org/0000-0002-7364-913X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling Jin","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007142915","display_name":"MA Xi-jun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xijun Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.02025539,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1389","last_page":"1392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9944000244140625,"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/T12031","display_name":"Speech and dialogue systems","score":0.9904000163078308,"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":0.8050243854522705},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7551167607307434},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.7220543026924133},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5523689985275269},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5272014737129211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45452937483787537},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.450324684381485},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.422014445066452},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33418214321136475},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.08812037110328674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050243854522705},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7551167607307434},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.7220543026924133},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5523689985275269},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5272014737129211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45452937483787537},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.450324684381485},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.422014445066452},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33418214321136475},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.08812037110328674},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-459","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-459","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W15130933","https://openalex.org/W75668230","https://openalex.org/W91484551","https://openalex.org/W1599623585","https://openalex.org/W1733696394","https://openalex.org/W2033010331","https://openalex.org/W2117849308","https://openalex.org/W2137851479"],"related_works":["https://openalex.org/W2982321410","https://openalex.org/W2392004567","https://openalex.org/W2046296964","https://openalex.org/W2940029036","https://openalex.org/W4388292429","https://openalex.org/W4389670110","https://openalex.org/W2756595502","https://openalex.org/W2429057255","https://openalex.org/W2187546663","https://openalex.org/W148745890"],"abstract_inverted_index":{"Corpus":[0],"based":[1],"Concatenative":[2],"Text-To-Speech":[3],"(CTTS)":[4],"systems":[5],"have":[6,97],"been":[7],"proven":[8,98],"a":[9,21,54,73,82],"successful":[10],"method":[11,76],"to":[12,41,46],"produce":[13],"good":[14],"voice":[15],"quality":[16,52],"speech.":[17],"However,":[18],"It":[19],"requires":[20],"large":[22],"inventory":[23,56],"of":[24,36,93],"synthesis":[25,51],"segments":[26,45],"and":[27,65,90],"complex":[28],"search":[29],"algorithms,":[30],"which":[31,78],"sometimes":[32],"hinder":[33],"the":[34,43,48,94],"usability":[35],"CTTS.":[37],"Segment":[38],"pre-selection":[39,75,106],"targets":[40],"prune":[42],"candidate":[44],"achieve":[47],"best":[49],"possible":[50],"within":[53],"pre-defined":[55],"size.":[57],"Making":[58],"CTTS":[59,112],"usable":[60],"in":[61,77,85,110],"environments":[62],"where":[63],"memory":[64],"CPU":[66],"are":[67],"critically":[68],"constrained.":[69],"This":[70],"paper":[71],"presents":[72],"novel":[74],"Mutual":[79],"Information":[80],"(MI),":[81],"well-known":[83],"concept":[84],"statistics,":[86],"is":[87],"integrated.":[88],"Objective":[89],"subjective":[91],"evaluations":[92],"synthesized":[95],"speech":[96],"that":[99],"this":[100],"new":[101],"approach":[102],"out-performs":[103],"two":[104],"conventional":[105],"methods":[107],"popularly":[108],"used":[109],"current":[111],"systems.":[113]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
