{"id":"https://openalex.org/W2963588163","doi":"https://doi.org/10.1109/icsda.2014.7051441","title":"F<inf>0</inf> modeling in HMM-based speech synthesis system using Deep Belief Network","display_name":"F<inf>0</inf> modeling in HMM-based speech synthesis system using Deep Belief Network","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2963588163","doi":"https://doi.org/10.1109/icsda.2014.7051441","mag":"2963588163"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2014.7051441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2014.7051441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (COCOSDA)","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/A5032597862","display_name":"Sankar Mukherjee","orcid":"https://orcid.org/0000-0003-3927-6365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sankar Mukherjee","raw_affiliation_strings":["Yantra Software, Hyderabad, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yantra Software, Hyderabad, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103503442","display_name":"Shyamal Kumar Das Mandal","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":false,"raw_author_name":"Shyamal Kumar Das Mandal","raw_affiliation_strings":["Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kharagpur, Kharagpur, West Bengal, IN","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4135,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63556367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"5"},"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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":0.9962999820709229,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7313058376312256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.643367350101471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6413541436195374},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6182554364204407},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6056331992149353},{"id":"https://openalex.org/keywords/bengali","display_name":"Bengali","score":0.506489634513855},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4944636821746826},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49142277240753174},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.48009541630744934},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4650237560272217},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4643592834472656},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45735445618629456},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36080747842788696},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3422809839248657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11692559719085693}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7313058376312256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.643367350101471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6413541436195374},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6182554364204407},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6056331992149353},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.506489634513855},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4944636821746826},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49142277240753174},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.48009541630744934},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4650237560272217},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4643592834472656},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45735445618629456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36080747842788696},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3422809839248657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11692559719085693},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsda.2014.7051441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2014.7051441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 17th Oriental Chapter of the International Committee for the Co-ordination and Standardization of Speech Databases and Assessment Techniques (COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W73112891","https://openalex.org/W1926768285","https://openalex.org/W2020024436","https://openalex.org/W2045158511","https://openalex.org/W2071399124","https://openalex.org/W2076638338","https://openalex.org/W2102003408","https://openalex.org/W2116064496","https://openalex.org/W2117130368","https://openalex.org/W2124914669","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2164700406","https://openalex.org/W2168013545","https://openalex.org/W2398366824","https://openalex.org/W2596135543","https://openalex.org/W4297796761","https://openalex.org/W6668594742","https://openalex.org/W6675380101","https://openalex.org/W6678801095","https://openalex.org/W6712441277","https://openalex.org/W6735255722"],"related_works":["https://openalex.org/W2084490135","https://openalex.org/W2895890526","https://openalex.org/W4298170800","https://openalex.org/W2794758919","https://openalex.org/W617692174","https://openalex.org/W2038801705","https://openalex.org/W2912305781","https://openalex.org/W161037869","https://openalex.org/W2688184458","https://openalex.org/W2904846757"],"abstract_inverted_index":{"In":[0,43],"recent":[1],"years":[2],"multilayer":[3],"perceptrons":[4],"(MLPs)":[5],"with":[6],"many":[7,19],"hidden":[8,90,96,99],"layers":[9,91],"Deep":[10,46],"Neural":[11],"Network":[12,48],"(DNN)":[13],"has":[14,38,55],"performed":[15],"surprisingly":[16],"well":[17],"in":[18,31,115,133,137],"speech":[20,23,27,66,72,118],"tasks,":[21],"i.e.":[22],"recognition,":[24],"speaker":[25],"verification,":[26],"synthesis":[28,73],"etc.":[29],"Although":[30],"the":[32,62],"context":[33],"of":[34,52,64,139],"F0modeling":[35],"these":[36],"techniques":[37,112],"not":[39],"been":[40,56],"exploited":[41],"properly.":[42],"this":[44],"paper,":[45],"Belief":[47],"(DBN),":[49],"a":[50,128],"class":[51],"DNN":[53],"family":[54],"employed":[57],"and":[58,92,103,141],"applied":[59],"to":[60,88,94],"model":[61],"F0contour":[63,136],"synthesized":[65],"which":[67,132],"was":[68,77,101],"generated":[69],"by":[70],"HMM-based":[71],"system.":[74],"The":[75,105],"experiment":[76],"done":[78],"on":[79],"Bengali":[80],"language.":[81],"Several":[82],"DBN-DNN":[83,126],"architectures":[84],"ranging":[85],"from":[86,123],"four":[87],"seven":[89],"up":[93],"200":[95],"units":[97],"per":[98],"layer":[100],"presented":[102],"evaluated.":[104],"results":[106],"were":[107],"compared":[108],"against":[109],"clustering":[110],"tree":[111],"popularly":[113],"found":[114],"statistical":[116],"parametric":[117],"synthesis.":[119],"We":[120],"show":[121],"that":[122],"textual":[124],"inputs":[125],"learns":[127],"high":[129],"level":[130],"structure":[131],"turn":[134],"improves":[135],"terms":[138],"objective":[140],"subjective":[142],"tests.":[143]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}