{"id":"https://openalex.org/W1964101772","doi":"https://doi.org/10.1109/ihci.2012.6481857","title":"Better human computer interaction by enhancing the quality of text-to-speech synthesis","display_name":"Better human computer interaction by enhancing the quality of text-to-speech synthesis","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1964101772","doi":"https://doi.org/10.1109/ihci.2012.6481857","mag":"1964101772"},"language":"en","primary_location":{"id":"doi:10.1109/ihci.2012.6481857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ihci.2012.6481857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 4th International Conference on Intelligent Human Computer Interaction (IHCI)","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":[{"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":true,"raw_author_name":"V. Ramu Reddy","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, Kharagpur 721302, West Bengal, India"],"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, Kharagpur 721302, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]}]},{"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, Kharagpur 721302, West Bengal, India"],"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, Kharagpur 721302, West Bengal, India","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034006373"],"corresponding_institution_ids":["https://openalex.org/I145894827"],"apc_list":null,"apc_paid":null,"fwci":1.7139,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85460368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"23","issue":null,"first_page":"1","last_page":"6"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9973999857902527,"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":0.996399998664856,"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/prosody","display_name":"Prosody","score":0.9439831972122192},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.72316575050354},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.6878937482833862},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6414315700531006},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5951879024505615},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.582610011100769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.50633704662323},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.484481543302536},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4673612117767334},{"id":"https://openalex.org/keywords/feedforward-neural-network","display_name":"Feedforward neural network","score":0.4506358504295349},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.4497680962085724},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.44267863035202026},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4188956320285797},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11810627579689026},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09553927183151245},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07451304793357849},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07144111394882202}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9439831972122192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72316575050354},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.6878937482833862},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6414315700531006},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5951879024505615},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.582610011100769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.50633704662323},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.484481543302536},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4673612117767334},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.4506358504295349},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.4497680962085724},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.44267863035202026},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4188956320285797},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11810627579689026},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09553927183151245},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07451304793357849},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07144111394882202},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ihci.2012.6481857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ihci.2012.6481857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 4th International Conference on Intelligent Human Computer Interaction (IHCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W178225857","https://openalex.org/W1979792881","https://openalex.org/W2048932243","https://openalex.org/W2060855080","https://openalex.org/W2075170185","https://openalex.org/W2086056075","https://openalex.org/W2086793370","https://openalex.org/W2112844139","https://openalex.org/W2124776405","https://openalex.org/W2547888173","https://openalex.org/W6607319171"],"related_works":["https://openalex.org/W1965454423","https://openalex.org/W2028501571","https://openalex.org/W2052542215","https://openalex.org/W2036564641","https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W2115072676","https://openalex.org/W157238252","https://openalex.org/W2169632867"],"abstract_inverted_index":{"In":[0,23,38],"this":[1,24,39],"paper":[2],"we":[3],"propose":[4],"high":[5],"quality":[6,12,95],"prosody":[7,26,41,70,81],"models":[8,42,71,82],"for":[9,17,119],"enhancing":[10],"the":[11,34,65,94,97,103,108],"of":[13,33,36,59,64,96],"text-to-speech":[14],"(TTS)":[15],"synthesis":[16],"providing":[18],"better":[19,118],"human":[20],"computer":[21],"interaction.":[22],"study":[25],"refers":[27],"to":[28,92,124],"duration":[29],"and":[30,49,56,77],"intonation":[31],"patterns":[32],"sequence":[35],"syllables.":[37,60],"work,":[40],"are":[43,89],"developed":[44],"using":[45],"feedforward":[46],"neural":[47,67,120],"networks,":[48],"prosodic":[50,105],"information":[51],"is":[52,72,112,117],"predicted":[53,104],"from":[54],"linguistic":[55],"production":[57],"constraints":[58],"The":[61],"prediction":[62,115],"accuracy":[63,116],"proposed":[66],"network":[68,121],"based":[69,80],"compared":[73,123],"objectively":[74],"with":[75],"Classification":[76],"Regression":[78],"Tree":[79],"used":[83],"by":[84,101],"Festival.":[85],"Subjective":[86],"listening":[87],"tests":[88],"also":[90],"performed":[91],"evaluate":[93],"synthesized":[98],"speech":[99],"generated":[100],"incorporating":[102],"features.":[106],"From":[107],"evaluation":[109],"studies,":[110],"it":[111],"observed":[113],"that":[114],"models,":[122],"other":[125],"models.":[126]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
