{"id":"https://openalex.org/W2124384059","doi":"https://doi.org/10.1109/icassp.2004.1327256","title":"SVM-based audio classification for instructional video analysis","display_name":"SVM-based audio classification for instructional video analysis","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2124384059","doi":"https://doi.org/10.1109/icassp.2004.1327256","mag":"2124384059"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1327256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1327256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100414156","display_name":"Ying Li","orcid":"https://orcid.org/0000-0002-1487-3350"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Li","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112870855","display_name":"Chitra Dorai","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chitra Dorai","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3721,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.93703925,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"V","last_page":"897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9926000237464905,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9563999772071838,"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/computer-science","display_name":"Computer science","score":0.8021520376205444},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.77652907371521},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6161060929298401},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.5481524467468262},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5206305384635925},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5006527900695801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4974868595600128},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.457484632730484},{"id":"https://openalex.org/keywords/decision-tree-learning","display_name":"Decision tree learning","score":0.4536539614200592},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.437398225069046},{"id":"https://openalex.org/keywords/classification-scheme","display_name":"Classification scheme","score":0.4176819920539856},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.396106481552124},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39443284273147583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3561055064201355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021520376205444},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.77652907371521},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6161060929298401},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.5481524467468262},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5206305384635925},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5006527900695801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4974868595600128},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.457484632730484},{"id":"https://openalex.org/C5481197","wikidata":"https://www.wikidata.org/wiki/Q16766476","display_name":"Decision tree learning","level":3,"score":0.4536539614200592},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.437398225069046},{"id":"https://openalex.org/C13460635","wikidata":"https://www.wikidata.org/wiki/Q85753676","display_name":"Classification scheme","level":2,"score":0.4176819920539856},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.396106481552124},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39443284273147583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3561055064201355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1327256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1327256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W139898027","https://openalex.org/W1576520375","https://openalex.org/W1894664571","https://openalex.org/W2081353817","https://openalex.org/W2121127941","https://openalex.org/W2125055259","https://openalex.org/W2128838222","https://openalex.org/W2139212933","https://openalex.org/W2140685304","https://openalex.org/W2144345993","https://openalex.org/W4255193866","https://openalex.org/W4285719527","https://openalex.org/W6605678257","https://openalex.org/W6639647816","https://openalex.org/W6680559069"],"related_works":["https://openalex.org/W2591672004","https://openalex.org/W1982169401","https://openalex.org/W2356463514","https://openalex.org/W4319437832","https://openalex.org/W4243803609","https://openalex.org/W2030894524","https://openalex.org/W2350430350","https://openalex.org/W2592385415","https://openalex.org/W102063058","https://openalex.org/W2006686080"],"abstract_inverted_index":{"Automatic":[0],"content":[1,23,72],"analysis":[2,73],"and":[3,8,74,83,107],"annotation":[4],"for":[5,69],"efficient":[6],"search":[7],"browsing":[9],"of":[10,21,35,117],"topics":[11],"in":[12,18],"instructional":[13,36],"videos":[14,37,86],"are":[15,53],"current":[16,29],"challenges":[17],"the":[19,33,44,66,101,103,108,115,118],"management":[20],"e-learning":[22],"repositories.":[24],"This":[25],"paper":[26],"presents":[27],"our":[28],"work":[30],"on":[31,80],"classifying":[32],"soundtrack":[34],"into":[38,60],"seven":[39],"distinct":[40],"audio":[41,62,110],"classes":[42],"using":[43],"support":[45],"vector":[46],"machine":[47],"(SVM)":[48],"technology.":[49],"The":[50,97],"classification":[51,95,111],"results":[52],"then":[54],"used":[55],"to":[56],"partition":[57],"a":[58],"video":[59],"homogeneous":[61],"segments,":[63],"which":[64],"forms":[65],"fundamental":[67],"basis":[68],"its":[70],"higher-level":[71],"exploration.":[75],"Initial":[76],"experiments":[77],"carried":[78],"out":[79],"three":[81],"education":[82],"four":[84],"training":[85],"totalling":[87],"185":[88],"minutes":[89],"have":[90],"yielded":[91],"an":[92],"average":[93],"97.9%":[94],"accuracy.":[96],"performance":[98],"comparisons":[99],"between":[100],"SVM-based,":[102],"decision":[104],"tree":[105],"(DT)-based":[106],"threshold-based":[109],"schemes":[112],"further":[113],"demonstrates":[114],"superiority":[116],"proposed":[119],"scheme.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}