{"id":"https://openalex.org/W4396852732","doi":"https://doi.org/10.1145/3647444.3647871","title":"Contextual transcription and Summarization of audio using AI","display_name":"Contextual transcription and Summarization of audio using AI","publication_year":2023,"publication_date":"2023-11-23","ids":{"openalex":"https://openalex.org/W4396852732","doi":"https://doi.org/10.1145/3647444.3647871"},"language":"en","primary_location":{"id":"doi:10.1145/3647444.3647871","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3647444.3647871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Information Management & Machine Intelligence","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/A5097927782","display_name":"Karan Pandita","orcid":"https://orcid.org/0009-0009-7888-7805"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Karan Pandita","raw_affiliation_strings":["Network and Communications, SRMIST, KTR, India"],"affiliations":[{"raw_affiliation_string":"Network and Communications, SRMIST, KTR, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097955612","display_name":"Purab Kulranjan Singh Thakur","orcid":"https://orcid.org/0009-0004-4173-4817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Purab Kulranjan Singh Thakur","raw_affiliation_strings":["Networking communications (NWC), SRM IST, KTR, India"],"affiliations":[{"raw_affiliation_string":"Networking communications (NWC), SRM IST, KTR, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103247536","display_name":"Suresh Annamalai","orcid":"https://orcid.org/0000-0001-7439-2834"},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suresh Annamalai","raw_affiliation_strings":["Networking and Communications, SRM Institute of Science and Technology, India"],"affiliations":[{"raw_affiliation_string":"Networking and Communications, SRM Institute of Science and Technology, India","institution_ids":["https://openalex.org/I145286018"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5097927782"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9796,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77272165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9814000129699707,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.9096291065216064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7485361695289612},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6988561749458313},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39045268297195435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37449222803115845},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3571610450744629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.325771689414978},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10434171557426453}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9096291065216064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485361695289612},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6988561749458313},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39045268297195435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37449222803115845},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3571610450744629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.325771689414978},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10434171557426453},{"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:10.1145/3647444.3647871","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3647444.3647871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Information Management & Machine Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W3045684855","https://openalex.org/W3127104351","https://openalex.org/W3198903637","https://openalex.org/W4200213295","https://openalex.org/W4308308868","https://openalex.org/W4367396672","https://openalex.org/W4378550189","https://openalex.org/W4378979140","https://openalex.org/W4381691320","https://openalex.org/W4382365868","https://openalex.org/W4385339509","https://openalex.org/W4385407701","https://openalex.org/W4385804261","https://openalex.org/W4386385376"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"The":[0],"field":[1],"of":[2,47,129,198],"Natural":[3],"Language":[4],"Processing":[5],"(NLP)":[6],"has":[7],"revolutionized":[8],"the":[9,130,165,196,203,214],"way":[10],"human":[11],"language":[12,149],"interacts":[13],"with":[14,45,210],"computer":[15],"systems.":[16],"NLP":[17,40,85,209],"applications":[18],"span":[19],"machine":[20],"translation,":[21],"information":[22],"extraction,":[23],"summarization,":[24],"and":[25,33,57,70,78,91,106,124,176,183],"question":[26],"answering,":[27],"driven":[28],"by":[29],"vast":[30],"computational":[31],"resources":[32],"big":[34],"data":[35,153],"methodologies.":[36],"Despite":[37],"these":[38],"advancements,":[39],"tools":[41,142],"haven't":[42],"fully":[43],"integrated":[44],"Internet":[46],"Things":[48],"(IoT)":[49],"devices,":[50,212],"like":[51,143,171],"audio":[52,68,101,193],"recorders,":[53],"hindering":[54],"their":[55],"accessibility":[56,156],"usability.":[58],"This":[59,133,200],"paper":[60],"introduces":[61],"an":[62],"innovative":[63],"solution:":[64],"a":[65,96,158,218],"method":[66],"for":[67,173,206],"transcription":[69],"contextual":[71],"summarization":[72],"using":[73],"NLP,":[74],"addressing":[75],"this":[76],"gap":[77],"enhancing":[79,155,195],"comprehension.":[80],"Our":[81,161],"approach":[82,201],"employs":[83],"cutting-edge":[84],"techniques,":[86],"including":[87],"word":[88],"embedding":[89],"methods":[90],"knowledge-based":[92,187],"graphs,":[93,188],"to":[94,168,217],"create":[95],"system":[97,147,190],"that":[98],"efficiently":[99],"converts":[100],"content":[102],"into":[103],"written":[104],"text":[105],"generates":[107],"coherent":[108],"summaries.":[109],"Unlike":[110],"existing":[111],"AI":[112],"tools,":[113],"our":[114,146,189],"system's":[115,166],"summaries":[116],"are":[117],"not":[118],"only":[119],"accurate":[120],"but":[121],"also":[122],"rich":[123],"deep,":[125],"providing":[126],"insightful":[127],"representations":[128],"original":[131],"content.":[132],"depth":[134],"is":[135],"achieved":[136],"through":[137],"advanced":[138],"linguistic":[139],"analysis,":[140],"surpassing":[141],"ChatGPT.":[144],"Furthermore,":[145],"breaks":[148],"barriers,":[150],"enabling":[151],"multilingual":[152],"traversal,":[154],"on":[157],"global":[159],"scale.":[160],"research":[162],"methodology":[163],"ensures":[164],"adherence":[167],"industry":[169],"standards":[170],"Request":[172],"Comments":[174],"(RFC)":[175],"Constrained":[177],"Application":[178],"Protocol":[179],"(CoAP),":[180],"guaranteeing":[181],"interoperability":[182],"reliability.":[184],"By":[185],"incorporating":[186],"comprehensively":[191],"understands":[192],"content,":[194],"accuracy":[197],"summarization.":[199],"addresses":[202],"unmet":[204],"need":[205],"seamlessly":[207],"integrating":[208],"IoT":[211],"making":[213],"technology":[215],"accessible":[216],"broader":[219],"audience.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}