{"id":"https://openalex.org/W23433745","doi":"https://doi.org/10.21437/interspeech.2004-451","title":"Perception-guided and phonetic clustering weight tuning based on diphone pairs for unit selection TTS","display_name":"Perception-guided and phonetic clustering weight tuning based on diphone pairs for unit selection TTS","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W23433745","doi":"https://doi.org/10.21437/interspeech.2004-451","mag":"23433745"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-451","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-451","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/A5054715999","display_name":"Francesc \u00c1l\u00edas","orcid":"https://orcid.org/0000-0002-1921-2375"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesc Alias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036640710","display_name":"Xavier Llor\u00e0","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Llora","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041510182","display_name":"Ignasi Iriondo","orcid":"https://orcid.org/0000-0003-2467-4192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ignasi Iriondo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086391751","display_name":"Joan Claudi Socor\u00f3","orcid":"https://orcid.org/0000-0002-7348-6916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joan Claudi Socoro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039293393","display_name":"Xavier Sevillano","orcid":"https://orcid.org/0000-0002-6209-3033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Sevillano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086183936","display_name":"Llu\u00eds Formiga","orcid":"https://orcid.org/0000-0001-9515-6611"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lluis Formiga","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2867,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.51908796,"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":"1221","last_page":"1224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7705351114273071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7704432010650635},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.721832811832428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5711895227432251},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5435343980789185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.509313702583313},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4834369122982025},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45728084444999695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32258182764053345},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.061668604612350464}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7705351114273071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704432010650635},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.721832811832428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5711895227432251},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5435343980789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.509313702583313},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4834369122982025},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45728084444999695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32258182764053345},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.061668604612350464},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-451","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-451","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W95427963","https://openalex.org/W112900918","https://openalex.org/W125901607","https://openalex.org/W164706226","https://openalex.org/W182288408","https://openalex.org/W242851985","https://openalex.org/W1492438950","https://openalex.org/W1550297032","https://openalex.org/W1594031697","https://openalex.org/W1599623585","https://openalex.org/W1639032689","https://openalex.org/W2123504579","https://openalex.org/W2150658333","https://openalex.org/W2151019861","https://openalex.org/W2904250082","https://openalex.org/W3010673478"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W2083665254","https://openalex.org/W2942177010"],"abstract_inverted_index":{"The":[0,86],"quality":[1],"of":[2,11,21,24,40,54,62,92],"corpus":[3],"based":[4,82],"text-to-speech":[5],"systems":[6],"depends":[7],"on":[8,18,32,83],"the":[9,12,19,22,25,38,51,57,90],"accuracy":[10],"unit":[13,73],"selection":[14,58],"process,":[15],"which":[16],"relies":[17],"values":[20],"weights":[23],"cost":[26],"function.":[27],"This":[28],"paper":[29],"is":[30],"focused":[31],"defining":[33],"a":[34,45,69],"new":[35],"framework":[36],"for":[37,47,72],"tuning":[39,81],"these":[41],"weights.":[42],"We":[43],"propose":[44],"technique":[46],"taking":[48],"into":[49],"account":[50],"subjective":[52],"perception":[53],"speech":[55],"in":[56],"process":[59],"by":[60],"means":[61],"Interactive":[63],"Genetic":[64],"Algorithms.":[65],"Moreover,":[66],"we":[67],"introduce":[68],"CARTbased":[70],"method":[71],"clustering.":[74],"Both":[75],"techniques":[76],"are":[77],"applied":[78],"to":[79],"weight":[80],"diphone":[84],"pairs.":[85],"conducted":[87],"experiments":[88],"analyze":[89],"feasibility":[91],"both":[93],"proposals":[94],"separately.":[95]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
