{"id":"https://openalex.org/W2167161853","doi":"https://doi.org/10.21437/interspeech.2005-619","title":"A comparison of methods for speaker-dependent pronunciation tuning for text-to-speech synthesis","display_name":"A comparison of methods for speaker-dependent pronunciation tuning for text-to-speech synthesis","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W2167161853","doi":"https://doi.org/10.21437/interspeech.2005-619","mag":"2167161853"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-619","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-619","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/A5084980276","display_name":"Gabriel Webster","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gabriel Webster","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050474660","display_name":"Tina Burrows","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tina Burrows","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032046290","display_name":"K.M. Knill","orcid":"https://orcid.org/0000-0003-1292-2769"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katherine Knill","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084980276"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4387,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75625988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2809","last_page":"2812"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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":0.9943000078201294,"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":0.882317066192627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8308150768280029},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.716823160648346},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6602262854576111},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6415292024612427},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6370830535888672},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.530665934085846},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.520238995552063},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5200918912887573},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4989633560180664},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11749830842018127}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.882317066192627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308150768280029},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.716823160648346},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6602262854576111},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6415292024612427},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6370830535888672},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.530665934085846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.520238995552063},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5200918912887573},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4989633560180664},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11749830842018127},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2005-619","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-619","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W45136203","https://openalex.org/W165351933","https://openalex.org/W180253589","https://openalex.org/W182288408","https://openalex.org/W184370862","https://openalex.org/W1572730534","https://openalex.org/W2021991837","https://openalex.org/W2117400858"],"related_works":["https://openalex.org/W2061937230","https://openalex.org/W2189081180","https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2152945827","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W301864623"],"abstract_inverted_index":{"Unit-based":[0],"text-to-speech":[1],"(TTS)":[2],"systems":[3],"typically":[4],"use":[5],"a":[6,18,39,85,91],"set":[7,20],"of":[8,21,38,41,46,54,58,69,106,128,143],"speech":[9,61,79,135],"recordings":[10],"that":[11],"have":[12,77],"been":[13],"phonetically":[14],"transcribed":[15],"to":[16,34,65,94,133],"create":[17],"large":[19],"phonetic":[22,42,56],"units.":[23,43],"During":[24],"synthesis,":[25],"pronunciations":[26,49,131],"for":[27,84,103],"input":[28],"text":[29,130,146],"are":[30],"generated":[31],"and":[32,114],"used":[33],"guide":[35],"the":[36,52,55,59,67,70,120,124,129,134,140,144],"selection":[37],"sequence":[40],"The":[44],"style":[45,53],"these":[47],"system":[48],"must":[50],"match":[51],"transcriptions":[57,136],"recorded":[60],"database":[62],"in":[63],"order":[64],"maximize":[66],"quality":[68],"synthesized":[71],"speech.":[72],"Furthermore,":[73],"since":[74],"different":[75,78],"speakers":[76,83],"characteristics,":[80],"supporting":[81],"multiple":[82],"single":[86],"language":[87],"generally":[88],"requires":[89],"applying":[90],"speaker-dependent":[92,107],"mapping":[93],"speaker-independent":[95],"pronunciations.":[96],"This":[97],"paper":[98],"investigates":[99],"three":[100],"automatic":[101],"methods":[102],"this":[104],"process":[105],"pronunciation":[108],"tuning:":[109],"word":[110],"N-grams,":[111],"decision":[112],"trees,":[113],"transformation-based":[115],"learning.":[116],"Transformation-based":[117],"learning":[118],"achieved":[119],"best":[121],"results,":[122],"lowering":[123],"phone":[125],"error":[126,141],"rate":[127,142],"compared":[132],"by":[137],"26%":[138],"over":[139],"unmodified":[145],"transcriptions.":[147]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}