{"id":"https://openalex.org/W2071643438","doi":"https://doi.org/10.1109/ncc.2014.6811347","title":"Automatic Phonetic Transcription for read, extempore and conversation speech for an Indian language: Bengali","display_name":"Automatic Phonetic Transcription for read, extempore and conversation speech for an Indian language: Bengali","publication_year":2014,"publication_date":"2014-02-01","ids":{"openalex":"https://openalex.org/W2071643438","doi":"https://doi.org/10.1109/ncc.2014.6811347","mag":"2071643438"},"language":"en","primary_location":{"id":"doi:10.1109/ncc.2014.6811347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2014.6811347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 Twentieth National Conference on Communications (NCC)","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/A5055592276","display_name":"K E Manjunath","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"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"K E Manjunath","raw_affiliation_strings":["Indian Institute of Technology Delhi, New Delhi, Delhi, IN","School of Information Technology, Indian Institute of Technology Kharagpur, India - 721302#TAB#"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi, New Delhi, Delhi, IN","institution_ids":["https://openalex.org/I68891433"]},{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Kharagpur, India - 721302#TAB#","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, India","School of Information Technology, Indian Institute of Technology Kharagpur, India - 721302#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Information Technology Indian Institute of Technology, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]},{"raw_affiliation_string":"School of Information Technology, Indian Institute of Technology Kharagpur, India - 721302#TAB#","institution_ids":["https://openalex.org/I145894827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055592276"],"corresponding_institution_ids":["https://openalex.org/I145894827","https://openalex.org/I68891433"],"apc_list":null,"apc_paid":null,"fwci":3.681,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.93696782,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"31","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":0.9987000226974487,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9616000056266785,"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/bengali","display_name":"Bengali","score":0.9207752346992493},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.8927044868469238},{"id":"https://openalex.org/keywords/phonetic-transcription","display_name":"Phonetic transcription","score":0.757663369178772},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7458086609840393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6727660298347473},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6682839393615723},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.550764262676239},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5314660668373108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5267583727836609},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4570661783218384},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44993215799331665},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.428314208984375},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3117936849594116},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.1916937232017517},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.14357692003250122}],"concepts":[{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.9207752346992493},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.8927044868469238},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.757663369178772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458086609840393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6727660298347473},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6682839393615723},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.550764262676239},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5314660668373108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5267583727836609},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4570661783218384},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44993215799331665},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.428314208984375},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3117936849594116},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.1916937232017517},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.14357692003250122},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ncc.2014.6811347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2014.6811347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 Twentieth National Conference on Communications (NCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310119","display_name":"Ministry of Communication and Information Technology","ror":"https://ror.org/05nmnwa45"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1499360075","https://openalex.org/W1560013842","https://openalex.org/W1741269295","https://openalex.org/W1977506353","https://openalex.org/W1980850109","https://openalex.org/W2049155070","https://openalex.org/W2061615302","https://openalex.org/W2151188193","https://openalex.org/W2465080433","https://openalex.org/W2544280297","https://openalex.org/W2546718992","https://openalex.org/W3133502865","https://openalex.org/W6662599187","https://openalex.org/W6790895672"],"related_works":["https://openalex.org/W97919259","https://openalex.org/W4283755617","https://openalex.org/W4250156791","https://openalex.org/W2103288531","https://openalex.org/W113515668","https://openalex.org/W4214593397","https://openalex.org/W2155576284","https://openalex.org/W2154680756","https://openalex.org/W1587721369","https://openalex.org/W132084023"],"abstract_inverted_index":{"In":[0,24,36,87],"this":[1,37,88],"work,":[2,27],"we":[3],"have":[4],"analyzed":[5],"the":[6,28,134,157],"proposed":[7],"Automatic":[8,71],"Phonetic":[9,72],"Transcription":[10,73],"(APT)":[11],"approach":[12],"for":[13,21,45,79,132,143,160],"read,":[14,80,96,144,161],"extempore":[15,81,97,145,162],"and":[16,47,55,82,98,106,120,146,163,169],"conversation":[17,83,99,147,164],"modes":[18,49,84,100,148,165],"of":[19,50,60,85,101],"speech":[20,51,102],"Bengali":[22,53],"language.":[23,69],"our":[25],"earlier":[26],"APT":[29,44,62,90,110],"was":[30],"carried":[31,93,113],"out":[32,94,114],"using":[33,103,115,141],"read":[34],"speech.":[35,86],"paper,":[38],"main":[39],"focus":[40],"is":[41],"on":[42,95],"deriving":[43,61],"Extempore":[46],"Conversation":[48],"in":[52],"language":[54],"their":[56],"analysis.":[57],"This":[58],"framework":[59],"can":[63],"be":[64],"extended":[65],"to":[66],"any":[67],"Indian":[68],"The":[70,136],"Systems":[74],"(APTS)":[75],"were":[76],"developed":[77],"separately":[78],"study,":[89],"has":[91,111],"been":[92,112],"35,":[104],"33":[105],"30":[107],"phones":[108],"respectively.":[109,154,171],"Hidden":[116],"Markov":[117],"Models":[118],"(HMMs)":[119],"FeedForward":[121],"Neural":[122],"Networks":[123],"(FFNNs).":[124],"Mel-frequency":[125],"Cepstral":[126],"Coefficients":[127],"are":[128,149,166],"used":[129],"as":[130],"features":[131],"building":[133],"models.":[135],"best":[137],"obtained":[138],"performance":[139],"accuracies":[140,159],"HMMs":[142],"41.65%,":[150],"29.20%":[151],"and,":[152],"23.48%":[153],"Using":[155],"FFNNs,":[156],"recognition":[158],"53.87%,":[167],"46.19%":[168],"33.63%":[170]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}