{"id":"https://openalex.org/W2510142453","doi":"https://doi.org/10.21437/interspeech.2016-864","title":"Improving TTS with Corpus-Specific Pronunciation Adaptation","display_name":"Improving TTS with Corpus-Specific Pronunciation Adaptation","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2510142453","doi":"https://doi.org/10.21437/interspeech.2016-864","mag":"2510142453"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-864","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","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/A5028709353","display_name":"Marie Tahon","orcid":"https://orcid.org/0000-0002-6782-0332"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Marie Tahon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030717896","display_name":"Raheel Qader","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raheel Qader","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002469975","display_name":"Gw\u00e9nol\u00e9 Lecorv\u00e9","orcid":"https://orcid.org/0000-0002-4271-2087"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gw\u00e9nol\u00e9 Lecorv\u00e9","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003200234","display_name":"Damien Lolive","orcid":"https://orcid.org/0000-0002-1110-5444"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Damien Lolive","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028709353"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7139,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.89027058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2831","last_page":"2835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9776999950408936,"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/T12031","display_name":"Speech and dialogue systems","score":0.9776999950408936,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9656000137329102,"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":0.9322999715805054,"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":0.8006271719932556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6950029730796814},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6762811541557312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5213310122489929},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43856117129325867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36164170503616333},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23985779285430908},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08054342865943909}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8006271719932556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6950029730796814},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6762811541557312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5213310122489929},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43856117129325867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36164170503616333},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23985779285430908},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08054342865943909},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2016-864","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W43307560","https://openalex.org/W183551973","https://openalex.org/W224303163","https://openalex.org/W831673790","https://openalex.org/W1533757633","https://openalex.org/W1990057706","https://openalex.org/W2015073768","https://openalex.org/W2026197747","https://openalex.org/W2035589087","https://openalex.org/W2079833689","https://openalex.org/W2106279089","https://openalex.org/W2118938353","https://openalex.org/W2119479037","https://openalex.org/W2160986985"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W1607396156","https://openalex.org/W2776838583","https://openalex.org/W2359469050","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Text-to-speech":[0],"(TTS)":[1],"systems":[2],"are":[3,9,27,83,100,132],"built":[4],"on":[5,115],"speech":[6,41,118,127,156],"corpora":[7],"which":[8],"labeled":[10],"with":[11,30,71],"carefully":[12],"checked":[13],"and":[14,79,108],"segmented":[15],"phonemes.":[16],"However,":[17],"phoneme":[18,105],"sequences":[19],"generated":[20,55],"by":[21],"automatic":[22],"grapheme-to-phoneme":[23],"converters":[24],"during":[25],"synthesis":[26,128],"usually":[28],"inconsistent":[29],"those":[31],"from":[32,139],"the":[33,48,58,93,124,135,143],"corpus,":[34],"thus":[35],"leading":[36],"to":[37,57,64,91],"poor":[38],"quality":[39,125],"synthetic":[40],"signals.":[42],"To":[43],"solve":[44],"this":[45],"problem":[46],",":[47],"present":[49],"work":[50],"aims":[51],"at":[52],"adapting":[53],"automatically":[54],"pronunciations":[56],"corpus.":[59],"The":[60],"main":[61],"idea":[62],"is":[63],"train":[65],"corpus-specific":[66],"phoneme-to-phoneme":[67],"conditional":[68],"random":[69],"fields":[70],"a":[72,116],"large":[73],"set":[74],"of":[75,104,126,154],"linguistic,":[76],"phonological,":[77],"articulatory":[78],"acoustic-prosodic":[80],"features.":[81],"Features":[82],"first":[84],"selected":[85],"in":[86,102,123,134,152],"cross-validation":[87],"condition,":[88],"then":[89],"combined":[90],"produce":[92],"final":[94],"best":[95],"feature":[96],"set.":[97],"Pronunciation":[98],"models":[99,131],"evaluated":[101],"terms":[103,153],"error":[106],"rate":[107],"through":[109],"perceptual":[110],"tests.":[111],"Experiments":[112],"carried":[113],"out":[114],"French":[117],"corpus":[119],"show":[120],"an":[121],"improvement":[122],"when":[129],"pronunciation":[130,145],"included":[133],"phonetization":[136],"process.":[137],"Appart":[138],"improving":[140],"TTS":[141],"quality,":[142],"presented":[144],"adaptation":[146],"method":[147],"also":[148],"brings":[149],"interesting":[150],"perspectives":[151],"expressive":[155],"synthesis.":[157]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
