{"id":"https://openalex.org/W2965150757","doi":"https://doi.org/10.1145/3330482.3330508","title":"Text-Independent Speaker ID for Automatic Video Lecture Classification Using Deep Learning","display_name":"Text-Independent Speaker ID for Automatic Video Lecture Classification Using Deep Learning","publication_year":2019,"publication_date":"2019-04-19","ids":{"openalex":"https://openalex.org/W2965150757","doi":"https://doi.org/10.1145/3330482.3330508","mag":"2965150757"},"language":"en","primary_location":{"id":"doi:10.1145/3330482.3330508","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330482.3330508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 5th International Conference on Computing and Artificial 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/A5044015235","display_name":"Ali Shariq Imran","orcid":"https://orcid.org/0000-0002-2416-2878"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Ali Shariq Imran","raw_affiliation_strings":["Dept. of Electronic Systems, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronic Systems, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052954560","display_name":"Zenun Kastrati","orcid":"https://orcid.org/0000-0002-0199-2377"},"institutions":[{"id":"https://openalex.org/I223464139","display_name":"Linnaeus University","ror":"https://ror.org/00j9qag85","country_code":"SE","type":"education","lineage":["https://openalex.org/I223464139"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zenun Kastrati","raw_affiliation_strings":["Dept. of Computer Science and Media Technology, Linnaeus University, V\u00e4xj\u00f6, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Media Technology, Linnaeus University, V\u00e4xj\u00f6, Sweden","institution_ids":["https://openalex.org/I223464139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055323428","display_name":"Torbj\u00f8rn Svendsen","orcid":"https://orcid.org/0000-0003-0578-7941"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Torbj\u00f8rn Karl Svendsen","raw_affiliation_strings":["Dept. of Electronic Systems, Faculty of Information Technology and Electrical Engineering, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronic Systems, Faculty of Information Technology and Electrical Engineering, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022616464","display_name":"Arianit Kurti","orcid":"https://orcid.org/0000-0003-0512-6350"},"institutions":[{"id":"https://openalex.org/I223464139","display_name":"Linnaeus University","ror":"https://ror.org/00j9qag85","country_code":"SE","type":"education","lineage":["https://openalex.org/I223464139"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Arianit Kurti","raw_affiliation_strings":["Dept. of Computer Science and Media Technology, Linnaeus University, V\u00e4xj\u00f6, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Media Technology, Linnaeus University, V\u00e4xj\u00f6, Sweden","institution_ids":["https://openalex.org/I223464139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1669,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44202325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"18","issue":null,"first_page":"175","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.996399998664856,"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/T10860","display_name":"Speech and Audio Processing","score":0.996399998664856,"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":0.9927999973297119,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8187386393547058},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5856429934501648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5146837830543518},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44786280393600464},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42387625575065613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3735385537147522},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.355191707611084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187386393547058},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5856429934501648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5146837830543518},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44786280393600464},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42387625575065613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3735385537147522},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.355191707611084}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3330482.3330508","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3330482.3330508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 5th International Conference on Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W161077313","https://openalex.org/W1578856370","https://openalex.org/W1978104871","https://openalex.org/W2031945826","https://openalex.org/W2090160423","https://openalex.org/W2096545806","https://openalex.org/W2099102065","https://openalex.org/W2290028669","https://openalex.org/W2497140328","https://openalex.org/W2506827292","https://openalex.org/W2509063695","https://openalex.org/W2549349626","https://openalex.org/W2563367938","https://openalex.org/W2748501745","https://openalex.org/W2752711828","https://openalex.org/W2807528251","https://openalex.org/W2900895635","https://openalex.org/W2903752916","https://openalex.org/W6635103661","https://openalex.org/W6744058167","https://openalex.org/W6815182717"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2611678594","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"to":[3,47,74],"use":[4],"acoustic":[5],"features":[6,73,79],"employing":[7],"deep":[8],"neural":[9,14],"network":[10,15],"(DNN)":[11],"and":[12,40,54,64],"convolutional":[13],"(CNN)":[16],"models":[17,30],"for":[18,38,41],"classifying":[19,42],"video":[20,44,91,99],"lectures":[21,92],"in":[22],"a":[23],"massive":[24],"open":[25],"online":[26],"course":[27],"(MOOC).":[28],"The":[29],"exploit":[31],"the":[32,36,43,48,75,83,90,95,98],"voice":[33],"pattern":[34],"of":[35],"lecturer":[37],"identification":[39],"lecture":[45],"according":[46],"right":[49],"speaker":[50],"category.":[51],"Filter":[52],"bank":[53],"Mel":[55],"frequency":[56],"cepstral":[57],"coefficient":[58],"(MFCC)":[59],"feature":[60],"along":[61],"with":[62],"first":[63],"second":[65],"order":[66],"derivatives":[67],"(\u0394/\u0394\u0394)":[68],"are":[69,80],"used":[70],"as":[71],"input":[72],"proposed":[76],"models.":[77],"These":[78],"extracted":[81],"from":[82,89,97],"speech":[84],"signal":[85],"which":[86],"is":[87],"obtained":[88],"by":[93],"separating":[94],"audio":[96],"using":[100],"FFmpeg.":[101]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
