{"id":"https://openalex.org/W7225795229","doi":"https://doi.org/10.5281/zenodo.24140193","title":"Speech Processing System with Real-Time Emotion and Accent Detection","display_name":"Speech Processing System with Real-Time Emotion and Accent Detection","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225795229","doi":"https://doi.org/10.5281/zenodo.24140193"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24140193","doi":"https://doi.org/10.5281/zenodo.24140193","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24140193","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24140193","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161441079","display_name":"Arya Swaraj","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arya Swaraj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161435805","display_name":"Aayush Singh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aayush Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5161445406","display_name":"Bibek Chaube","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bibek Chaube","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9628999829292297,"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":0.9628999829292297,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.028999999165534973,"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":0.0034000000450760126,"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":[],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7778000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7470999956130981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7221999764442444},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6359000205993652},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.6104000210762024},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.4219000041484833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3700999915599823},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3167000114917755},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.26080000400543213},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24140193","doi":"https://doi.org/10.5281/zenodo.24140193","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24140193","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24140194","doi":"https://doi.org/10.5281/zenodo.24140194","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24140194","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24140193","doi":"https://doi.org/10.5281/zenodo.24140193","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24140193","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Speech":[0],"processing":[1,50],"has":[2],"become":[3],"an":[4,47],"important":[5],"com-ponent":[6],"of":[7,142,183],"modern":[8],"human\u2013computer":[9],"interaction":[10],"systems,":[11,159],"en-abling":[12],"computers":[13],"to":[14,19,42,145,154],"understand,":[15],"analyze,":[16],"and":[17,61,89,106,118,162,180],"respond":[18],"spokencommunication.":[20],"Conventional":[21],"speech":[22,31,49,54,59,82,114,163],"applications":[23],"generally":[24],"con-centrate":[25],"on":[26],"individual":[27],"tasks":[28],"such":[29],"as":[30],"recognition,":[32,55,115],"voicesynthesis,":[33],"or":[34,74],"classification.":[35],"However,":[36],"practical":[37],"speech-analysisapplications":[38],"require":[39],"multiple":[40],"capabilities":[41],"operate":[43],"together.This":[44],"paper":[45,166],"presents":[46,167],"AI-based":[48],"systemthat":[51],"integrates":[52],"automatic":[53],"accent":[56,86,116],"detection,emotion":[57],"detection,":[58],"analytics,":[60],"real-time":[62],"voice":[63],"interac-tion":[64],"within":[65],"a":[66,136],"unified":[67,137],"web":[68],"platform.":[69],"The":[70,121,149],"proposed":[71,133,172],"system":[72,122,150,185],"acceptsuploaded":[73],"live-recorded":[75],"speech,":[76],"performs":[77],"audio":[78],"preprocessingand":[79],"normalization,":[80],"converts":[81],"into":[83],"text,":[84],"detects":[85],"andemotional":[87],"characteristics,":[88],"generates":[90],"analytical":[91],"feedback.The":[92],"frontend":[93],"is":[94],"implemented":[95],"using":[96],"React.js,":[97],"while":[98],"FastAPI":[99],"isused":[100],"for":[101,113],"backend":[102],"communication,":[103],"authentication,":[104],"asynchronousprocessing,":[105],"persistent":[107],"data":[108],"management.":[109],"Machine-learningmodels":[110],"are":[111],"incorporated":[112],"classifi-cation,":[117],"emotion":[119],"analysis.":[120],"additionally":[123],"calculatesspeech":[124],"duration,":[125],"speaking":[126],"rate,":[127],"frequently":[128],"occurring":[129],"words,":[130],"andclassification":[131],"confidence.The":[132],"architecture":[134],"provides":[135],"environment":[138],"forspeech":[139],"analysis":[140],"instead":[141],"requiring":[143],"users":[144],"access":[146],"multipleindependent":[147],"applications.":[148],"can":[151],"be":[152],"applied":[153],"languagelearning,":[155],"communication":[156],"training,":[157],"accessibility":[158],"conver-sational":[160],"assistants,":[161],"analytics.":[164],"This":[165],"theliterature":[168],"survey,":[169],"research":[170],"gap,":[171],"architecture,":[173],"processingpipeline,":[174],"machine-learning":[175],"models,":[176],"implementation,":[177],"evaluationmethodology,":[178],"limitations,":[179],"future":[181],"scope":[182],"the":[184]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}