{"id":"https://openalex.org/W4403724028","doi":"https://doi.org/10.1109/iacis61494.2024.10721926","title":"WhisperSum: Unified Audio-to-Text Summarization","display_name":"WhisperSum: Unified Audio-to-Text Summarization","publication_year":2024,"publication_date":"2024-08-23","ids":{"openalex":"https://openalex.org/W4403724028","doi":"https://doi.org/10.1109/iacis61494.2024.10721926"},"language":"en","primary_location":{"id":"doi:10.1109/iacis61494.2024.10721926","doi":"https://doi.org/10.1109/iacis61494.2024.10721926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iacis61494.2024.10721926","pdf_url":null,"source":{"id":"https://openalex.org/S7407096113","display_name":"International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5111968285","display_name":"S. Ganguly","orcid":"https://orcid.org/0009-0008-6561-2362","observed_orcids":["https://orcid.org/0009-0008-6561-2362"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sayam Ganguly","raw_affiliation_strings":["TINT,Dept of CSE,Kolkata,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TINT,Dept of CSE,Kolkata,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014860518","display_name":"Sourav Mandal","orcid":"https://orcid.org/0000-0002-6066-8008","observed_orcids":["https://orcid.org/0000-0002-6066-8008"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sourav Mandal","raw_affiliation_strings":["TINT,Dept of CSE,Kolkata,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TINT,Dept of CSE,Kolkata,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056627205","display_name":"Nabanita Das","orcid":"https://orcid.org/0000-0001-7879-0071","observed_orcids":["https://orcid.org/0000-0001-7879-0071"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nabanita Das","raw_affiliation_strings":["TINT,Dept of CSE,Kolkata,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TINT,Dept of CSE,Kolkata,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015569746","display_name":"Bikash Sadhukhan","orcid":"https://orcid.org/0000-0001-5469-0711","observed_orcids":["https://orcid.org/0000-0001-5469-0711"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bikash Sadhukhan","raw_affiliation_strings":["TINT,Dept of CSE,Kolkata,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TINT,Dept of CSE,Kolkata,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sagarika Sarkar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sagarika Sarkar","raw_affiliation_strings":["TINT,Dept of CSE,Kolkata,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TINT,Dept of CSE,Kolkata,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070149804","display_name":"Swagata Paul","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swagata Paul","raw_affiliation_strings":["TINT,Dept of CSE,Kolkata,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TINT,Dept of CSE,Kolkata,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6108,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68601491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8744999766349792,"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":0.8744999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.04050000011920929,"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/T10028","display_name":"Topic Modeling","score":0.02630000002682209,"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/speech-to-text-transcription","display_name":"speech-to-text transcription","score":0.8180000185966492},{"id":"https://openalex.org/keywords/whisper","display_name":"Whisper","score":0.5979999899864197},{"id":"https://openalex.org/keywords/spacy","display_name":"spaCy","score":0.9610000252723694},{"id":"https://openalex.org/keywords/extractive-summarization","display_name":"extractive summarization","score":0.9100000262260437},{"id":"https://openalex.org/keywords/audio-summarization","display_name":"audio summarization","score":0.7879999876022339},{"id":"https://openalex.org/keywords/web-application","display_name":"web application","score":0.7450000047683716},{"id":"https://openalex.org/keywords/flask","display_name":"Flask","score":0.5830000042915344},{"id":"https://openalex.org/keywords/information-overload","display_name":"information overload","score":0.7480000257492065}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8774130940437317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983744144439697},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33328258991241455},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28255563974380493}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iacis61494.2024.10721926","doi":"https://doi.org/10.1109/iacis61494.2024.10721926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iacis61494.2024.10721926","pdf_url":null,"source":{"id":"https://openalex.org/S7407096113","display_name":"International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2952911430","https://openalex.org/W3004241745","https://openalex.org/W3042185737","https://openalex.org/W3081986567","https://openalex.org/W3099994082","https://openalex.org/W3168205992","https://openalex.org/W3170450402","https://openalex.org/W3190367510","https://openalex.org/W3199683498","https://openalex.org/W3217119495","https://openalex.org/W4200068734","https://openalex.org/W4205464839","https://openalex.org/W4224957132","https://openalex.org/W4226502708","https://openalex.org/W4289344424","https://openalex.org/W4291710825","https://openalex.org/W4306318603","https://openalex.org/W4312221408","https://openalex.org/W4321488478","https://openalex.org/W4393354653","https://openalex.org/W6913039581"],"related_works":["https://openalex.org/W7135229982","https://openalex.org/W7117562985","https://openalex.org/W4410111587","https://openalex.org/W7167694925","https://openalex.org/W4399261414","https://openalex.org/W4411214979","https://openalex.org/W7130707898","https://openalex.org/W6911926465","https://openalex.org/W7108201813","https://openalex.org/W4416426541"],"abstract_inverted_index":{"In":[0],"an":[1],"era":[2],"overwhelmed":[3],"by":[4,146],"information,":[5,153],"efficiently":[6],"extracting":[7],"relevant":[8],"data":[9],"from":[10],"audio":[11,41,71,117],"sources":[12],"is":[13,128],"crucial.":[14],"This":[15],"study":[16],"introduces":[17],"WhisperSum,":[18],"a":[19,66,137],"solution":[20,139],"combining":[21],"OpenAI's":[22],"Whisper":[23],"for":[24,35,69,130],"accurate":[25],"voice":[26],"transcription":[27,82,163],"with":[28,84,98],"spaCy's":[29],"advanced":[30,160],"natural":[31],"language":[32],"processing":[33],"(NLP)":[34],"extractive":[36],"text":[37],"summarization.":[38],"WhisperSum":[39,94,143],"transcribes":[40],"files":[42],"into":[43],"text,":[44],"analyzes":[45],"the":[46,85,148,155],"content,":[47],"and":[48,75,92,101,106,115,122,134,162],"produces":[49],"concise":[50],"summaries":[51],"to":[52,140],"help":[53],"users":[54],"quickly":[55],"understand":[56],"key":[57],"information.":[58],"The":[59,78,126],"web":[60],"application,":[61],"built":[62],"using":[63],"Flask,":[64],"offers":[65],"user-friendly":[67],"interface":[68],"easy":[70],"uploads,":[72],"real-time":[73],"transcription,":[74],"summary":[76],"retrieval.":[77],"system":[79],"integrates":[80],"Whisper's":[81],"capabilities":[83],"NLP":[86,161],"tools":[87],"of":[88,103,151,158],"spaCy,":[89],"ensuring":[90,147],"accuracy":[91],"efficiency.":[93],"achieved":[95],"high":[96],"performance,":[97],"precision,":[99],"recall,":[100],"F1-scores":[102],"91.98%,":[104],"92.12%,":[105],"92.04%,":[107],"respectively,":[108],"highlighting":[109],"its":[110],"effectiveness":[111],"in":[112],"accurately":[113],"transcribing":[114],"summarizing":[116],"content":[118,131],"while":[119],"minimizing":[120],"errors":[121],"maintaining":[123],"comprehensive":[124],"coverage.":[125],"application":[127],"valuable":[129],"management,":[132],"education,":[133],"journalism,":[135],"providing":[136],"streamlined":[138],"information":[141],"overload.":[142],"enhances":[144],"decision-making":[145],"accessible":[149],"availability":[150],"crucial":[152],"demonstrating":[154],"significant":[156],"potential":[157],"integrating":[159],"technologies.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2024-10-25T00:00:00"}
