{"id":"https://openalex.org/W4248034423","doi":"https://doi.org/10.23919/eusipco54536.2021.9616310","title":"An Audio-Based Deep Learning Framework For BBC Television Programme Classification","display_name":"An Audio-Based Deep Learning Framework For BBC Television Programme Classification","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W4248034423","doi":"https://doi.org/10.23919/eusipco54536.2021.9616310"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616310","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616310","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5075250567","display_name":"Lam Pham","orcid":"https://orcid.org/0000-0001-8155-7553"},"institutions":[{"id":"https://openalex.org/I4210110242","display_name":"Digital Science (United States)","ror":"https://ror.org/020h4b682","country_code":"US","type":"company","lineage":["https://openalex.org/I4210110242","https://openalex.org/I4210112888","https://openalex.org/I4210118830"]},{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]},{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["AT","GB","US"],"is_corresponding":true,"raw_author_name":"Lam Pham","raw_affiliation_strings":["Center for Digital Safety & Security, Austrian Institute of Technology, Austria","Center for Vision Speech and Signal Processing, University of Surrey, UK","Security, Austrian Institute of Technology, Austria","Center for Digital Safety &#x0026"],"affiliations":[{"raw_affiliation_string":"Center for Digital Safety & Security, Austrian Institute of Technology, Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Center for Vision Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Security, Austrian Institute of Technology, Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Center for Digital Safety &#x0026","institution_ids":["https://openalex.org/I4210110242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014883159","display_name":"Chris Baume","orcid":"https://orcid.org/0000-0002-9799-8596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Baume","raw_affiliation_strings":["BBC Research and Development, BBC, UK"],"affiliations":[{"raw_affiliation_string":"BBC Research and Development, BBC, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["ByteDance AI Lab,ByteDance,China"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab,ByteDance,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089443958","display_name":"Tassadaq Hussain","orcid":"https://orcid.org/0000-0003-1396-5429"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tassadaq Hussain","raw_affiliation_strings":["Center for Vision Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Center for Vision Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Center for Vision Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Center for Vision Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Plumbley","raw_affiliation_strings":["Center for Vision Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Center for Vision Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075250567"],"corresponding_institution_ids":["https://openalex.org/I132118926","https://openalex.org/I28290843","https://openalex.org/I4210110242"],"apc_list":null,"apc_paid":null,"fwci":1.0325,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83647376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9803000092506409,"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":0.9635999798774719,"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/discriminative-model","display_name":"Discriminative model","score":0.8335474133491516},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7978278398513794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7400020956993103},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6429885029792786},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6266863346099854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5745397806167603},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5333191156387329},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4936710298061371},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4668581783771515},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4633994400501251},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3783648908138275},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3441880941390991},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2764732241630554},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06744319200515747},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.058973997831344604}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8335474133491516},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7978278398513794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7400020956993103},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6429885029792786},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6266863346099854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5745397806167603},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5333191156387329},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4936710298061371},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4668581783771515},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4633994400501251},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3783648908138275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3441880941390991},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2764732241630554},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06744319200515747},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.058973997831344604},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616310","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616310","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G2275550772","display_name":null,"funder_award_id":"EP/R511791/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1634005169","https://openalex.org/W1665214252","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W2016902084","https://openalex.org/W2022399098","https://openalex.org/W2032894676","https://openalex.org/W2091419168","https://openalex.org/W2095705004","https://openalex.org/W2101234009","https://openalex.org/W2142526407","https://openalex.org/W2145871814","https://openalex.org/W2163174791","https://openalex.org/W2171565413","https://openalex.org/W2191779130","https://openalex.org/W2258198666","https://openalex.org/W2593116425","https://openalex.org/W2768188490","https://openalex.org/W2963230557","https://openalex.org/W2963590343","https://openalex.org/W3094550259","https://openalex.org/W3105315310","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6654663746","https://openalex.org/W6674330103","https://openalex.org/W6675354045","https://openalex.org/W6687152286","https://openalex.org/W6745930336"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2011227383","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W2793814466"],"abstract_inverted_index":{"This":[0,110],"paper":[1],"proposes":[2],"a":[3,26,71,85],"deep":[4],"learning":[5],"framework":[6,117],"for":[7,44,73,118],"classification":[8,102,123],"of":[9,35,87,104,114,121,124],"BBC":[10],"television":[11,61,125],"programmes":[12,76,89],"using":[13],"audio.":[14],"The":[15],"audio":[16,41],"is":[17],"firstly":[18],"transformed":[19],"into":[20,25,70,77],"spectrograms,":[21],"which":[22],"are":[23,52,68,82],"fed":[24,69],"pre-trained":[27],"Convolutional":[28],"Neural":[29],"Network":[30],"(CNN),":[31],"obtaining":[32],"predicted":[33,46],"probabilities":[34,47],"sound":[36,50],"events":[37,51],"occurring":[38],"in":[39],"the":[40,45,60,64,75,96,112,115,119],"recording.":[42],"Statistics":[43],"and":[48],"detected":[49],"then":[53],"calculated":[54],"to":[55,91],"extract":[56],"discriminative":[57],"features":[58,66],"representing":[59],"programmes.":[62,126],"Finally,":[63],"embedded":[65],"extracted":[67],"classifier":[72],"classifying":[74],"different":[78],"genres.":[79],"Our":[80],"experiments":[81],"conducted":[83],"over":[84,106],"dataset":[86],"6,160":[88],"belonging":[90],"nine":[92],"genres":[93],"labelled":[94],"by":[95],"BBC.":[97],"We":[98],"achieve":[99],"an":[100],"average":[101],"accuracy":[103],"93.7%":[105],"14-fold":[107],"cross":[108],"validation.":[109],"demonstrates":[111],"efficacy":[113],"proposed":[116],"task":[120],"audio-based":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-23T07:41:27.035349","created_date":"2025-10-10T00:00:00"}