{"id":"https://openalex.org/W11074920","doi":"https://doi.org/10.21437/interspeech.2009-194","title":"Improving consistence of phonetic transcription for text-to-speech","display_name":"Improving consistence of phonetic transcription for text-to-speech","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W11074920","doi":"https://doi.org/10.21437/interspeech.2009-194","mag":"11074920"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051689632","display_name":"Pablo Daniel Ag\u00fcero","orcid":null},"institutions":[{"id":"https://openalex.org/I189075073","display_name":"National University of Mar del Plata","ror":"https://ror.org/055eqsb67","country_code":"AR","type":"education","lineage":["https://openalex.org/I189075073"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Pablo Daniel Ag\u00fcero","raw_affiliation_strings":["National University of Mar Del Plata"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Mar Del Plata","institution_ids":["https://openalex.org/I189075073"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024281798","display_name":"Juan Carlos Tulli","orcid":null},"institutions":[{"id":"https://openalex.org/I189075073","display_name":"National University of Mar del Plata","ror":"https://ror.org/055eqsb67","country_code":"AR","type":"education","lineage":["https://openalex.org/I189075073"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Juan Carlos Tulli","raw_affiliation_strings":["National University of Mar del Plata, Mar del Plata, Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Mar del Plata, Mar del Plata, Argentina","institution_ids":["https://openalex.org/I189075073"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"536","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.8007020950317383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7861905097961426},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7696632146835327},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.7563652992248535},{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.6654404997825623},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.629743218421936},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.562864363193512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5307322144508362},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4992523193359375},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4963095784187317},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.48412999510765076},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.4747890830039978},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4678286910057068},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3873261511325836},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.3550316393375397},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.14884090423583984},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.1378537118434906},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12386131286621094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007020950317383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7861905097961426},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7696632146835327},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.7563652992248535},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.6654404997825623},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.629743218421936},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.562864363193512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5307322144508362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4992523193359375},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4963095784187317},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.48412999510765076},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.4747890830039978},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4678286910057068},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3873261511325836},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3550316393375397},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.14884090423583984},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.1378537118434906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12386131286621094},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-194","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W70888257","https://openalex.org/W97413234","https://openalex.org/W114226241","https://openalex.org/W120415783","https://openalex.org/W1484551227","https://openalex.org/W1506212051","https://openalex.org/W2086182527","https://openalex.org/W2109862664","https://openalex.org/W2117400858","https://openalex.org/W2148233665","https://openalex.org/W2150658333","https://openalex.org/W2169711598"],"related_works":["https://openalex.org/W2110804267","https://openalex.org/W2027039380","https://openalex.org/W2161573742","https://openalex.org/W97919259","https://openalex.org/W2083557891","https://openalex.org/W2462492290","https://openalex.org/W2115782554","https://openalex.org/W4250156791","https://openalex.org/W2518728926","https://openalex.org/W132084023"],"abstract_inverted_index":{"Grapheme-to-phoneme":[0],"conversion":[1],"is":[2,85],"an":[3,34,72,78],"important":[4],"step":[5],"in":[6,15,74,93],"speech":[7,101,103,105],"segmentation":[8],"and":[9,52,63],"synthesis.":[10],"Many":[11],"approaches":[12],"are":[13,66],"proposed":[14],"the":[16,31,39,45,49,75,91],"literature":[17],"to":[18,43],"perform":[19],"appropriate":[20],"transcriptions:":[21],"CART,":[22],"FST,":[23],"HMM,":[24],"etc.":[25],"In":[26],"this":[27],"paper":[28],"we":[29],"propose":[30],"use":[32],"of":[33,90],"automatic":[35],"algorithm":[36],"that":[37],"uses":[38],"transformation-based":[40],"errordriven":[41],"learning":[42],"match":[44],"phonetic":[46,94],"transcription":[47,76,95],"with":[48],"speaker\u2019s":[50],"dialect":[51],"style.":[53],"Different":[54],"transcriptions":[55],"based":[56],"on":[57],"word,":[58],"part-of-speech":[59],"tags,":[60],"weak":[61],"forms":[62],"phonotactic":[64],"rules":[65],"validated.":[67],"The":[68,81],"experimental":[69],"results":[70],"show":[71],"improvement":[73],"using":[77],"objective":[79],"measure.":[80],"articulation":[82],"MOS":[83],"score":[84],"also":[86],"improved,":[87],"as":[88],"most":[89],"changes":[92],"affect":[96],"coarticulation":[97],"effects.":[98],"Index":[99],"Terms:":[100],"synthesis,":[102],"intelligibility,":[104],"recognition,":[106],"Hidden":[107],"Markov":[108],"models":[109]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}