{"id":"https://openalex.org/W2394527820","doi":"https://doi.org/10.1109/icassp.2016.7472679","title":"Analysis of natural and synthetic speech using Fujisaki model","display_name":"Analysis of natural and synthetic speech using Fujisaki model","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2394527820","doi":"https://doi.org/10.1109/icassp.2016.7472679","mag":"2394527820"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5071210435","display_name":"Tanvina Patel","orcid":"https://orcid.org/0000-0002-9544-0038"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tanvina B. Patel","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India, Gandhinagar, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), India, Gandhinagar, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4416,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7832305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"5250","last_page":"5254"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/T12031","display_name":"Speech and dialogue systems","score":0.9914000034332275,"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/speech-synthesis","display_name":"Speech synthesis","score":0.8222177028656006},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8067637085914612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7744910717010498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7513574957847595},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7169731855392456},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5511401295661926},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5505063533782959},{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.5060638785362244},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5051186680793762},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.4955507516860962},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4953845739364624},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48171573877334595},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43662580847740173},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.43513181805610657},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.4331846833229065},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4299246072769165},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.42823946475982666},{"id":"https://openalex.org/keywords/pitch-contour","display_name":"Pitch contour","score":0.4257495701313019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4232194125652313},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.3867035210132599},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.06937918066978455},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06660988926887512}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8222177028656006},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8067637085914612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744910717010498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7513574957847595},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7169731855392456},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5511401295661926},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5505063533782959},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.5060638785362244},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5051186680793762},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.4955507516860962},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4953845739364624},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48171573877334595},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43662580847740173},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.43513181805610657},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.4331846833229065},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4299246072769165},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.42823946475982666},{"id":"https://openalex.org/C2777895490","wikidata":"https://www.wikidata.org/wiki/Q7198848","display_name":"Pitch contour","level":2,"score":0.4257495701313019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4232194125652313},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.3867035210132599},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.06937918066978455},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06660988926887512},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W178225857","https://openalex.org/W344150399","https://openalex.org/W1496801689","https://openalex.org/W1546892833","https://openalex.org/W1915396584","https://openalex.org/W1997240284","https://openalex.org/W2022226126","https://openalex.org/W2053019885","https://openalex.org/W2071399124","https://openalex.org/W2082330413","https://openalex.org/W2107860279","https://openalex.org/W2112659417","https://openalex.org/W2112844139","https://openalex.org/W2117418893","https://openalex.org/W2129142580","https://openalex.org/W2138878452","https://openalex.org/W2398431249","https://openalex.org/W3044514286","https://openalex.org/W3127686677","https://openalex.org/W6611766843","https://openalex.org/W6629685604","https://openalex.org/W6712446845","https://openalex.org/W6781138257"],"related_works":["https://openalex.org/W2057176891","https://openalex.org/W2972679570","https://openalex.org/W4205602488","https://openalex.org/W3201059718","https://openalex.org/W3088575574","https://openalex.org/W1505164792","https://openalex.org/W101536429","https://openalex.org/W2081321698","https://openalex.org/W1890221585","https://openalex.org/W1993425621"],"abstract_inverted_index":{"Text-to-speech":[0],"(TTS)":[1],"synthesis":[2,17,24,68],"systems":[3,25,72],"are":[4,27],"being":[5],"advanced":[6],"to":[7,38,42,66,77,84,147,176,183,192],"achieve":[8],"naturalness":[9],"and":[10,19,92,116,125,144,158,188],"intelligibility":[11],"in":[12,30,59,114,156,166,171],"synthetic":[13,34,63,93,117,163],"speech.":[14,64,94,118,178],"Unit":[15],"selection-based":[16],"(USS)":[18],"Hidden":[20],"Markov":[21],"Model-based":[22],"text-to-speech":[23],"(HTS)":[26],"recent":[28],"techniques":[29],"this":[31,96],"area.":[32],"USS-based":[33,62],"speech":[35,46,54,67,122,164],"is":[36,55,82],"known":[37],"be":[39],"natural":[40,45,58,91,115,177],"(due":[41],"concatenation":[43],"of":[44,102,104,121,142,168],"sound":[47],"units).":[48],"On":[49],"the":[50,86,100,140,149],"other":[51],"hand,":[52],"HTS-based":[53],"not":[56],"as":[57,61,174],"perception":[60],"Due":[65],"technologies,":[69],"voice":[70],"biometrics":[71],"may":[73,181],"face":[74],"threats":[75],"due":[76],"impostor":[78,194],"attacks.":[79,195],"Thus,":[80],"it":[81],"important":[83],"study":[85],"differences":[87],"that":[88,162],"exist":[89],"between":[90,151],"In":[95],"context,":[97],"we":[98],"investigate":[99],"effectiveness":[101,141],"parameters":[103],"Fujisaki":[105],"model":[106],"for":[107],"capturing":[108],"Fundamental":[109],"frequency":[110],"(F0)":[111],"contour":[112,120],"variations":[113],"F0":[119],"contains":[123],"linguistic":[124],"non-linguistic":[126],"information.":[127],"Experimental":[128],"results":[129],"on":[130],"several":[131],"utterances":[132],"from":[133],"Gujarati":[134],"(a":[135],"low":[136],"resourced":[137],"language)":[138],"demonstrate":[139],"phrase":[143,157],"accent":[145,159],"components":[146,160],"analyze":[148],"difference":[150],"these":[152,185],"two":[153,186],"speeches.":[154],"Variability":[155],"suggests":[161],"differs":[165],"terms":[167],"prosodic":[169],"information":[170],"excitation":[172],"source":[173],"compared":[175],"These":[179],"findings":[180],"assist":[182],"distinguish":[184],"speeches":[187],"provide":[189],"an":[190],"aid":[191],"alleviate":[193]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}