{"id":"https://openalex.org/W2031720040","doi":"https://doi.org/10.1109/isda.2013.6920727","title":"High quality text-to-speech synthesis system with efficient duration models developed using coding schemes based on vowel production characteristics","display_name":"High quality text-to-speech synthesis system with efficient duration models developed using coding schemes based on vowel production characteristics","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2031720040","doi":"https://doi.org/10.1109/isda.2013.6920727","mag":"2031720040"},"language":"en","primary_location":{"id":"doi:10.1109/isda.2013.6920727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isda.2013.6920727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 13th International Conference on Intellient Systems Design and Applications","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/A5034006373","display_name":"V. Ramu Reddy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"V. Ramu Reddy","raw_affiliation_strings":["TCS Innovation Labs, Kolkata, West Bengal, India","TCS Innovation Labs, Kolkata, West Bengal-700 091, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Innovation Labs, Kolkata, West Bengal, India","institution_ids":[]},{"raw_affiliation_string":"TCS Innovation Labs, Kolkata, West Bengal-700 091, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048234263","display_name":"K. Sreenivasa Rao","orcid":"https://orcid.org/0000-0002-2186-0419"},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Sreenivasa Rao","raw_affiliation_strings":["School of Information Technology, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","School of Information Technology, Indian Institute of Technology Kharagpur - 721 302, West Bengal, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Kharagpur - 721 302, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08534556,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"306","issue":null,"first_page":"7","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9961000084877014,"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":0.7043553590774536},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7007759809494019},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.6803961992263794},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6514092087745667},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5803801417350769},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5106602311134338},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.509713351726532},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5066609978675842},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.4697552025318146},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.43068838119506836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3423681855201721},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17853057384490967},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07958158850669861},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07153412699699402}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7043553590774536},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7007759809494019},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6803961992263794},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6514092087745667},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5803801417350769},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5106602311134338},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.509713351726532},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5066609978675842},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.4697552025318146},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.43068838119506836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3423681855201721},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17853057384490967},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07958158850669861},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07153412699699402},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isda.2013.6920727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isda.2013.6920727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 13th International Conference on Intellient Systems Design and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1603808762","https://openalex.org/W1964101772","https://openalex.org/W1964376316","https://openalex.org/W2048932243","https://openalex.org/W2060855080","https://openalex.org/W2075170185","https://openalex.org/W2086056075","https://openalex.org/W2086793370","https://openalex.org/W2104714048","https://openalex.org/W2124776405","https://openalex.org/W2242296555","https://openalex.org/W2766039569","https://openalex.org/W6690281413"],"related_works":["https://openalex.org/W2121231314","https://openalex.org/W2300973977","https://openalex.org/W2025869674","https://openalex.org/W2334129531","https://openalex.org/W2515097069","https://openalex.org/W2074460168","https://openalex.org/W2053531689","https://openalex.org/W4300049944","https://openalex.org/W1978136968","https://openalex.org/W1842536210"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"encoding":[3],"schemes":[4,15,71],"based":[5,101],"on":[6,102],"production":[7,31],"characteristics":[8],"of":[9,13,21,23,48,69,77,84],"vowels.":[10],"The":[11,67,82],"performance":[12],"coding":[14,70],"is":[16,72,88],"analyzed":[17],"for":[18,44,64],"accurate":[19],"prediction":[20],"durations":[22,47],"syllables":[24],"using":[25],"neural":[26,62],"network":[27,63],"models.":[28,66],"Linguistic":[29],"and":[30,38,79],"constraints":[32],"represented":[33],"by":[34,75,93],"positional,":[35],"contextual,":[36],"phonological":[37],"articulatory":[39],"(PCPA)":[40],"features":[41,51],"are":[42,52],"used":[43],"predicting":[45],"the":[46,61,95],"syllables.":[49],"These":[50],"coded":[53,100],"with":[54,98],"distinct":[55],"numerical":[56],"values":[57],"before":[58],"feeding":[59],"to":[60,90],"building":[65],"evaluation":[68],"carried":[73],"out":[74],"means":[76],"objective":[78],"subjective":[80],"measures.":[81],"quality":[83],"text-to-speech":[85],"synthesis":[86],"system":[87],"observed":[89],"be":[91],"better":[92],"incorporating":[94],"duration":[96],"model":[97],"vowels":[99],"lip":[103],"roundness.":[104]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}