{"id":"https://openalex.org/W2736005052","doi":"https://doi.org/10.1109/ijcnn.2017.7965997","title":"Improved speaker recognition system for stressed speech using deep neural networks","display_name":"Improved speaker recognition system for stressed speech using deep neural networks","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2736005052","doi":"https://doi.org/10.1109/ijcnn.2017.7965997","mag":"2736005052"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7965997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","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/A5069966738","display_name":"Sri Harsha Dumpala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sri Harsha Dumpala","raw_affiliation_strings":["TCS Innovation Labs, Mumbai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Innovation Labs, Mumbai","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047383705","display_name":"Sunil Kumar Kopparapu","orcid":"https://orcid.org/0000-0002-0502-527X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunil Kumar Kopparapu","raw_affiliation_strings":["TCS Innovation Labs, Mumbai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Innovation Labs, Mumbai","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4458,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86731526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1257","last_page":"1264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9973999857902527,"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":0.9775999784469604,"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/speech-recognition","display_name":"Speech recognition","score":0.8160752058029175},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7774558067321777},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7470942735671997},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6503189206123352},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5856323838233948},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5547147393226624},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5159335732460022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5025832653045654},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4801085293292999},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47214558720588684},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37145495414733887}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8160752058029175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7774558067321777},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7470942735671997},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6503189206123352},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5856323838233948},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5547147393226624},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5159335732460022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5025832653045654},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4801085293292999},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47214558720588684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37145495414733887}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2017.7965997","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W105311456","https://openalex.org/W1006777433","https://openalex.org/W1494198834","https://openalex.org/W1987783679","https://openalex.org/W1998345532","https://openalex.org/W2004497042","https://openalex.org/W2009118216","https://openalex.org/W2011236050","https://openalex.org/W2041823554","https://openalex.org/W2046015436","https://openalex.org/W2046056978","https://openalex.org/W2067301010","https://openalex.org/W2073017590","https://openalex.org/W2118177361","https://openalex.org/W2121812409","https://openalex.org/W2129379984","https://openalex.org/W2136879537","https://openalex.org/W2150769028","https://openalex.org/W2153903782","https://openalex.org/W2165880886","https://openalex.org/W2180844708","https://openalex.org/W2344822617","https://openalex.org/W2398313355","https://openalex.org/W2401684398","https://openalex.org/W2405950182","https://openalex.org/W2407857848","https://openalex.org/W2515254866","https://openalex.org/W2962853205","https://openalex.org/W2963963943","https://openalex.org/W4234330420","https://openalex.org/W6639916541","https://openalex.org/W6662018943","https://openalex.org/W6677842065","https://openalex.org/W6704529918","https://openalex.org/W6712511187","https://openalex.org/W6712785922"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W106647055","https://openalex.org/W1992796048","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162"],"abstract_inverted_index":{"Good":[0],"speaker":[1,7,37,83,122],"recognition":[2,38,84,123],"systems":[3,63,95],"should":[4],"identify":[5],"the":[6,26,32,36,42,61,115,121,141,150],"irrespective":[8],"of":[9,28,35,108,120,143],"what":[10],"is":[11,39,58,86,136],"spoken,":[12],"including":[13],"non-speech":[14],"sounds":[15,30,99,110],"that":[16,60,106,139],"are":[17],"often":[18],"produced":[19],"during":[20],"natural":[21],"conversations.":[22],"In":[23],"this":[24],"work,":[25],"inclusion":[27,107],"breath":[29,98,109],"in":[31,82,111,132],"training":[33,94,112],"phase":[34],"analyzed":[40],"using":[41],"popular":[43],"Gaussian":[44],"mixture":[45],"model-universal":[46],"background":[47],"model":[48],"(GMM-UBM)":[49],"and":[50,100],"deep":[51],"neural":[52],"network":[53],"(DNN)":[54],"based":[55],"systems.":[56,79],"It":[57,135],"shown":[59,138],"DNN-based":[62],"have":[64],"a":[65],"better":[66],"learning":[67],"capability":[68],"to":[69,77,130,148],"perform":[70],"well":[71],"even":[72,152],"on":[73,88,125,153],"unseen":[74,89,154],"data":[75,92,113],"compared":[76],"GMM-UBM-based":[78],"Specifically,":[80],"enhancement":[81],"performance":[85,151],"obtained":[87],"stressed":[90,126],"speech":[91,127],"by":[93,128],"with":[96],"both":[97],"modal":[101],"speech.":[102],"Experimental":[103],"results":[104],"show":[105],"reduces":[114],"equal":[116],"error":[117],"rate":[118],"(EER)":[119],"system":[124],"40%":[129],"50%":[131],"absolute":[133],"terms.":[134],"also":[137],"increasing":[140],"number":[142],"hidden":[144],"layers":[145],"help":[146],"DNNs":[147],"improve":[149],"data.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}