{"id":"https://openalex.org/W145426695","doi":"https://doi.org/10.21437/interspeech.2005-793","title":"Unit selection synthesis database development using utterance verification","display_name":"Unit selection synthesis database development using utterance verification","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W145426695","doi":"https://doi.org/10.21437/interspeech.2005-793","mag":"145426695"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-793","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5042683465","display_name":"Ingunn Amdal","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Ingunn Amdal","raw_affiliation_strings":["Norwegian Univ. of Sci. and Tech"],"affiliations":[{"raw_affiliation_string":"Norwegian Univ. of Sci. and Tech","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055323428","display_name":"Torbj\u00f8rn Svendsen","orcid":"https://orcid.org/0000-0003-0578-7941"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Torbj\u00f8rn Svendsen","raw_affiliation_strings":["Norwegian Univ. of Sci. and Tech"],"affiliations":[{"raw_affiliation_string":"Norwegian Univ. of Sci. and Tech","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042683465"],"corresponding_institution_ids":["https://openalex.org/I204778367"],"apc_list":null,"apc_paid":null,"fwci":1.3701,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83703556,"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":"2553","last_page":"2556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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/T11309","display_name":"Music and Audio Processing","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8715338706970215},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8481999635696411},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7398229837417603},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6316198110580444},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5455065369606018},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5200569033622742},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5175561308860779},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4962778687477112},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4332432150840759},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42122209072113037},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3936702013015747}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8715338706970215},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8481999635696411},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7398229837417603},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6316198110580444},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5455065369606018},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5200569033622742},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5175561308860779},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4962778687477112},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4332432150840759},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42122209072113037},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3936702013015747},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2005-793","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.490.1260","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.490.1260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.iet.ntnu.no/projects/fonema/files/unit_selection_synt.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.594.1206","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.594.1206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.korfint.no/ingunn/publications/interspeech2005.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7200000286102295,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W44632420","https://openalex.org/W45136203","https://openalex.org/W1572730534","https://openalex.org/W1847897332","https://openalex.org/W2002087363","https://openalex.org/W2543977149","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2529301793","https://openalex.org/W2350724007","https://openalex.org/W2384121599","https://openalex.org/W2355751417","https://openalex.org/W2038083449","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390"],"abstract_inverted_index":{"Accurate":[0],"annotation":[1,41,73],"of":[2,8,14],"the":[3,12,29,54,84,102,119,123,133,142,159],"unit":[4,15,58],"inventory":[5],"database":[6,26],"is":[7,42,90,97,107],"vi-tal":[9],"importance":[10],"to":[11,31,51,63,92,148,153],"quality":[13],"selection":[16],"text-to-speech":[17],"synthesis.":[18,67],"The":[19,87],"time":[20],"consuming":[21],"manual":[22,61,160],"work":[23],"involved":[24],"in":[25,47],"development":[27],"limits":[28],"ability":[30],"produce":[32],"new":[33,72],"voices":[34],"quickly":[35],"and":[36,45,56,105,122],"at":[37],"low":[38],"cost.":[39],"Automatic":[40],"therefore":[43],"more":[44,46],"use.":[48],"Misalignments":[49],"due":[50],"mismatch":[52,100],"between":[53,101],"predicted":[55,103],"pronounced":[57],"sequence":[59],"require":[60],"correc-tion":[62],"achieve":[64],"natural":[65],"sounding":[66],"This":[68],"paper":[69],"proposes":[70],"a":[71,98,127],"assessment":[74],"method":[75],"using":[76],"log":[77],"likelihood":[78],"ratio":[79],"based":[80],"utterance":[81,143],"verification":[82,89,144],"on":[83],"recorded":[85],"database.":[86],"ut-terance":[88],"applied":[91,147],"detect":[93],"utterances":[94,131,150],"where":[95,111],"there":[96],"likely":[99],"pronunciation":[104],"what":[106],"actually":[108],"spoken,":[109],"or":[110],"an":[112],"automated":[113,129],"procedure":[114],"for":[115,170],"phonemic":[116],"labelling":[117],"misaligns":[118],"phone":[120],"labels":[121],"acoustic":[124],"content.":[125],"In":[126,139],"fully":[128],"procedure,":[130],"failing":[132],"ver-ification":[134],"test":[135],"can":[136,145],"be":[137,146,154],"discarded.":[138],"semi-automatic":[140],"procedures,":[141],"select":[149],"that":[151,166],"need":[152],"manually":[155],"inspected,":[156],"thereby":[157],"reducing":[158],"ef-fort.":[161],"Preliminary":[162],"experiments":[163],"are":[164],"presented":[165],"show":[167],"promis-ing":[168],"figures":[169],"correct":[171],"rejections.":[172],"1.":[173]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
