{"id":"https://openalex.org/W45136203","doi":"https://doi.org/10.21437/interspeech.2004-483","title":"Pronunciation lexicon adaptation for TTS voice building","display_name":"Pronunciation lexicon adaptation for TTS voice building","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W45136203","doi":"https://doi.org/10.21437/interspeech.2004-483","mag":"45136203"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-483","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-483","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/A5066280625","display_name":"Yeon-Jun Kim","orcid":"https://orcid.org/0000-0003-4732-2501"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yeon-Jun Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002689895","display_name":"Ann K. Syrdal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ann Syrdal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028548414","display_name":"Alistair Conkie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alistair Conkie","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066280625"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3106,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8881346,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2569","last_page":"2572"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9927999973297119,"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/pronunciation","display_name":"Pronunciation","score":0.8469033241271973},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.7456538677215576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7222051620483398},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6096546649932861},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5607004165649414},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4747638702392578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3477073311805725},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.30948615074157715},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09498286247253418}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8469033241271973},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.7456538677215576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222051620483398},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6096546649932861},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5607004165649414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4747638702392578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3477073311805725},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.30948615074157715},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09498286247253418},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-483","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-483","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.188.80","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.80","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/%7Ettsweb/tts/papers/2004_ICSLP/lexadapt.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W17875541","https://openalex.org/W1579089397","https://openalex.org/W1594082249","https://openalex.org/W2535170820"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W1831473261","https://openalex.org/W4293870971"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"reducing":[3],"phone":[4],"label":[5],"errors":[6,64],"in":[7],"TTS":[8,56],"voice":[9,57],"building":[10],"by":[11],"means":[12],"of":[13,15,42,54],"modeling":[14],"speaker":[16,20,75],"pronunciation":[17,48,63],"variants.":[18],"Each":[19],"has":[21],"his":[22],"or":[23],"her":[24],"own":[25],"unique":[26],"pronunciations":[27,71],"(and":[28],"context-dependent":[29],"variations),":[30],"so":[31],"that":[32,65,85,98],"no":[33],"one":[34],"standard":[35],"lexicon":[36],"is":[37],"able":[38],"to":[39,60,102],"cover":[40],"all":[41],"the":[43,74],"speaker\u2019s":[44],"variations.":[45],"Creating":[46],"speaker-dependent":[47],"lexicons":[49],"for":[50,105],"automatic":[51],"speech":[52],"labeling":[53],"our":[55,99],"databases":[58],"helped":[59],"eliminate":[61],"many":[62],"resulted":[66],"from":[67],"mismatches":[68],"between":[69],"lexical":[70],"and":[72,109],"how":[73],"(voice":[76],"talent)":[77],"actually":[78],"pronounced":[79],"a":[80],"word.":[81],"We":[82],"also":[83],"found":[84],"it":[86],"contributed":[87,101],"other":[88],"synthesis":[89],"quality":[90],"improvement":[91,104],"as":[92],"well.":[93],"A":[94],"perceptual":[95],"test":[96],"showed":[97],"work":[100],"MOS":[103],"American":[106],"English":[107],"male":[108],"female":[110],"voices.":[111],"1.":[112]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
