{"id":"https://openalex.org/W2786846112","doi":"https://doi.org/10.1109/apsipa.2017.8282109","title":"Importance of non-uniform prosody modification for speech recognition in emotion conditions","display_name":"Importance of non-uniform prosody modification for speech recognition in emotion conditions","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786846112","doi":"https://doi.org/10.1109/apsipa.2017.8282109","mag":"2786846112"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5063564167","display_name":"Vishnu Vidyadhara Raju","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"V. V. Vidyadhara Raju","raw_affiliation_strings":["Speech and Vision Lab, Kohli Center on Intelligent Systems, IIIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"Speech and Vision Lab, Kohli Center on Intelligent Systems, IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014351336","display_name":"Hari Krishna Vydana","orcid":"https://orcid.org/0000-0001-5192-5888"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hari Krishna Vydana","raw_affiliation_strings":["Speech and Vision Lab, Kohli Center on Intelligent Systems, IIIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"Speech and Vision Lab, Kohli Center on Intelligent Systems, IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058673990","display_name":"Suryakanth V. Gangashetty","orcid":"https://orcid.org/0000-0001-6745-4363"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suryakanth V Gangashetty","raw_affiliation_strings":["Speech and Vision Lab, Kohli Center on Intelligent Systems, IIIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"Speech and Vision Lab, Kohli Center on Intelligent Systems, IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007569113","display_name":"Anil Kumar Vuppala","orcid":"https://orcid.org/0000-0001-7795-0408"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anil Kumar Vuppala","raw_affiliation_strings":["Speech and Vision Lab, Kohli Center on Intelligent Systems, IIIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"Speech and Vision Lab, Kohli Center on Intelligent Systems, IIIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063564167"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":0.4352,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70858383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"573","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.9435012936592102},{"id":"https://openalex.org/keywords/emotive","display_name":"Emotive","score":0.9392598867416382},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7609078884124756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6901007890701294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6275573968887329},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.570765495300293},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.4531264305114746},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3338530957698822},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15217849612236023},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13154268264770508}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9435012936592102},{"id":"https://openalex.org/C2776215170","wikidata":"https://www.wikidata.org/wiki/Q5373820","display_name":"Emotive","level":2,"score":0.9392598867416382},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7609078884124756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6901007890701294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6275573968887329},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.570765495300293},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.4531264305114746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3338530957698822},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15217849612236023},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13154268264770508},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/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/apsipa.2017.8282109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W11625191","https://openalex.org/W28791135","https://openalex.org/W1629068926","https://openalex.org/W1989344925","https://openalex.org/W1992561557","https://openalex.org/W2080748494","https://openalex.org/W2089787547","https://openalex.org/W2112844139","https://openalex.org/W2113751256","https://openalex.org/W2143166897","https://openalex.org/W2144033509","https://openalex.org/W2153077516","https://openalex.org/W2161736993","https://openalex.org/W2294336071","https://openalex.org/W2296496557","https://openalex.org/W2397393582","https://openalex.org/W2428180336","https://openalex.org/W2586711829","https://openalex.org/W4390926574","https://openalex.org/W6682725998","https://openalex.org/W6696962386"],"related_works":["https://openalex.org/W3125311141","https://openalex.org/W3125648561","https://openalex.org/W2947571721","https://openalex.org/W2580934630","https://openalex.org/W2371680609","https://openalex.org/W2088122245","https://openalex.org/W4246492857","https://openalex.org/W2362773009","https://openalex.org/W258725851","https://openalex.org/W1965454423"],"abstract_inverted_index":{"A":[0],"mismatch":[1,21],"in":[2,11,31,35,41,62,155,173,184],"training":[3],"and":[4,48,89,106,120,149],"operating":[5],"environments":[6],"causes":[7],"a":[8],"performance":[9,57,76,157],"degradation":[10],"speech":[12,30,36,59,74,115,126,141,171],"recognition":[13,60,75,142,172],"systems":[14,61],"(ASR).":[15],"One":[16],"major":[17],"reason":[18],"for":[19,99,125,135,144,170],"this":[20],"is":[22,52,91,116,133,151,160,168,186],"due":[23,188],"to":[24,189],"the":[25,39,42,56,63,73,79,95,100,104,129,137,145,156,163,190],"presence":[26,64],"of":[27,45,58,65,86,113,158,175,192],"expressive":[28],"(emotive)":[29],"operational":[32],"environments.":[33],"Emotions":[34],"majorly":[37],"inflict":[38],"changes":[40],"prosody":[43,84,122,164,194],"parameters":[44],"pitch,":[46,87],"duration":[47,88],"energy.":[49],"This":[50,68],"work":[51,69],"aimed":[53],"at":[54],"improving":[55,72],"emotive":[66,114,166,177],"speech.":[67],"focuses":[70],"on":[71],"without":[77],"disturbing":[78],"existing":[80],"ASR":[81,138,159],"system.":[82,139],"The":[83,110,140],"modification":[85,96,123,195],"energy":[90],"achieved":[92],"by":[93],"tuning":[94],"factors":[97],"values":[98],"relative":[101],"differences":[102],"between":[103],"neutral":[105,111],"emotional":[107],"data":[108],"sets.":[109],"version":[112],"generated":[117],"using":[118],"uniform":[119],"non-uniform":[121,193],"methods":[124],"recognition.":[127],"During":[128],"study,":[130],"IITKGP-SESC":[131],"corpus":[132],"used":[134,169],"building":[136],"system":[143],"emotions":[146],"(anger,":[147],"happy":[148],"compassion)":[150],"evaluated.":[152],"An":[153,179],"improvement":[154,181],"observed":[161,187],"when":[162],"modified":[165],"utterance":[167],"place":[174],"original":[176],"utterance.":[178],"average":[180],"around":[182],"5%":[183],"accuracy":[185],"use":[191],"methods.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}