{"id":"https://openalex.org/W4294406066","doi":"https://doi.org/10.1186/s13636-022-00253-8","title":"A large TV dataset for speech and music activity detection","display_name":"A large TV dataset for speech and music activity detection","publication_year":2022,"publication_date":"2022-09-03","ids":{"openalex":"https://openalex.org/W4294406066","doi":"https://doi.org/10.1186/s13636-022-00253-8"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-022-00253-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00253-8","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00253-8","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00253-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005504900","display_name":"Yun-Ning Hung","orcid":"https://orcid.org/0000-0002-7242-6903"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yun-Ning Hung","raw_affiliation_strings":["Music Informatics Group, Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":"https://orcid.org/0000-0002-7242-6903","affiliations":[{"raw_affiliation_string":"Music Informatics Group, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055058138","display_name":"Chih-Wei Wu","orcid":"https://orcid.org/0000-0002-9019-6515"},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chih-Wei Wu","raw_affiliation_strings":["Netflix, Inc., Los Gatos, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netflix, Inc., Los Gatos, USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016069022","display_name":"Iroro Orife","orcid":null},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iroro Orife","raw_affiliation_strings":["Netflix, Inc., Los Gatos, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netflix, Inc., Los Gatos, USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074746266","display_name":"Aaron J. Hipple","orcid":null},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Hipple","raw_affiliation_strings":["Netflix, Inc., Los Gatos, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netflix, Inc., Los Gatos, USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033480644","display_name":"William Wolcott","orcid":"https://orcid.org/0009-0001-6772-8202"},"institutions":[{"id":"https://openalex.org/I869089601","display_name":"Netflix (United States)","ror":"https://ror.org/0197qw696","country_code":"US","type":"company","lineage":["https://openalex.org/I869089601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Wolcott","raw_affiliation_strings":["Netflix, Inc., Los Gatos, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netflix, Inc., Los Gatos, USA","institution_ids":["https://openalex.org/I869089601"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048454242","display_name":"Alexander Lerch","orcid":"https://orcid.org/0000-0001-6319-578X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Lerch","raw_affiliation_strings":["Music Informatics Group, Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Informatics Group, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005504900"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.1903,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77824128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"2022","issue":"1","first_page":null,"last_page":null},"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":0.9991999864578247,"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":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.8276612758636475},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7100977301597595},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6942552924156189},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5805369019508362},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5275746583938599},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4869869649410248},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4723528325557709},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4612267315387726},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45998093485832214},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4316195249557495},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4125578999519348},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3399622142314911}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276612758636475},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7100977301597595},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6942552924156189},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5805369019508362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5275746583938599},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4869869649410248},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4723528325557709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4612267315387726},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45998093485832214},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4316195249557495},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4125578999519348},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3399622142314911},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-022-00253-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00253-8","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00253-8","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bc6bd6ecb8334b98a892ae19bb54edac","is_oa":true,"landing_page_url":"https://doaj.org/article/bc6bd6ecb8334b98a892ae19bb54edac","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2022, Iss 1, Pp 1-12 (2022)","raw_type":"article"},{"id":"pmh:oai:zenodo.org:7025971","is_oa":true,"landing_page_url":"https://zenodo.org/record/7025971","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"info:eu-repo/semantics/other"}],"best_oa_location":{"id":"doi:10.1186/s13636-022-00253-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00253-8","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00253-8","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4294406066.pdf","grobid_xml":"https://content.openalex.org/works/W4294406066.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1964726488","https://openalex.org/W2062170755","https://openalex.org/W2085457662","https://openalex.org/W2133049755","https://openalex.org/W2137197207","https://openalex.org/W2151305614","https://openalex.org/W2408239454","https://openalex.org/W2568529987","https://openalex.org/W2803417255","https://openalex.org/W2899201823","https://openalex.org/W2937168415","https://openalex.org/W2981733351","https://openalex.org/W2997857663","https://openalex.org/W3013018143","https://openalex.org/W3123506934","https://openalex.org/W3139878283","https://openalex.org/W3140416159","https://openalex.org/W3143835353","https://openalex.org/W3165587897","https://openalex.org/W3198670780","https://openalex.org/W4237225249","https://openalex.org/W4249476504","https://openalex.org/W4249990232","https://openalex.org/W6603625323","https://openalex.org/W6611217216","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W2118717649","https://openalex.org/W410723623","https://openalex.org/W2413243053","https://openalex.org/W2015341305","https://openalex.org/W4225593417","https://openalex.org/W2035068594","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W3207796226","https://openalex.org/W2342291550"],"abstract_inverted_index":{"Abstract":[0],"Automatic":[1],"speech":[2,90,193],"and":[3,17,24,32,43,67,80,91,102,135,157,189,194],"music":[4,92,195],"activity":[5],"detection":[6],"(SMAD)":[7],"is":[8,111,148,174],"an":[9],"enabling":[10],"task":[11],"that":[12,144,180],"can":[13],"help":[14],"segment,":[15],"index,":[16],"pre-process":[18],"audio":[19,78,187],"content":[20],"in":[21],"radio":[22],"broadcast":[23],"TV":[25],"programs.":[26],"However,":[27],"due":[28],"to":[29,150,159],"copyright":[30],"concerns":[31],"the":[33,38,47,86,121,124,167,175],"cost":[34],"of":[35,41,49,75,89,123,169],"manual":[36],"annotation,":[37],"limited":[39],"availability":[40],"diverse":[42],"sizeable":[44],"datasets":[45],"hinders":[46],"progress":[48],"state-of-the-art":[50],"(SOTA)":[51],"data-driven":[52],"approaches.":[53],"We":[54],"address":[55],"this":[56,172],"challenge":[57],"by":[58,108],"presenting":[59],"a":[60,115,153],"large-scale":[61],"dataset":[62,147,173,179],"containing":[63],"Mel":[64],"spectrogram,":[65],"VGGish,":[66],"MFCCs":[68],"features":[69,182],"extracted":[70,183],"from":[71,184],"around":[72],"1600":[73],"h":[74],"professionally":[76,185],"produced":[77,186],"tracks":[79,188],"their":[81,136,190],"corresponding":[82,191],"noisy":[83],"labels":[84,95],"indicating":[85],"approximate":[87],"location":[88],"segments.":[93],"The":[94,141],"are":[96],"several":[97,129],"sources":[98],"such":[99],"as":[100,114,152],"subtitles":[101],"cuesheet.":[103],"A":[104],"test":[105],"set":[106],"curated":[107],"human":[109],"annotators":[110],"also":[112],"included":[113],"subset":[116],"for":[117],"evaluation.":[118],"To":[119,166],"validate":[120],"generalizability":[122],"proposed":[125,146],"dataset,":[126],"we":[127],"conduct":[128],"experiments":[130],"comparing":[131],"various":[132,163],"model":[133],"architectures":[134],"variants":[137],"under":[138],"different":[139],"conditions.":[140],"results":[142],"suggest":[143],"our":[145,170],"able":[149],"serve":[151],"reliable":[154],"training":[155],"resource":[156],"leads":[158],"SOTA":[160],"performances":[161],"on":[162],"public":[164],"datasets.":[165],"best":[168],"knowledge,":[171],"first":[176],"large-scale,":[177],"open-sourced":[178],"contains":[181],"frame-level":[192],"annotations.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}