{"id":"https://openalex.org/W2063631923","doi":"https://doi.org/10.1109/slt.2014.7078560","title":"Background-tracking acoustic features for genre identification of broadcast shows","display_name":"Background-tracking acoustic features for genre identification of broadcast shows","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2063631923","doi":"https://doi.org/10.1109/slt.2014.7078560","mag":"2063631923"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1509.04934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058841753","display_name":"\u00d3scar Saz","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Oscar Saz","raw_affiliation_strings":["Speech and Hearing Group, University of Sheffield, UK","Speech and Hearing Group, Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Group, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Group, Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037893785","display_name":"Mortaza Doulaty","orcid":"https://orcid.org/0000-0002-1773-7557"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mortaza Doulaty","raw_affiliation_strings":["Speech and Hearing Group, University of Sheffield, UK","Speech and Hearing Group, Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Group, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Group, Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Speech and Hearing Group, University of Sheffield, UK","Speech and Hearing Group, Department of Computer Science, University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Group, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Group, Department of Computer Science, University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058841753"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":2.3538,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.89224015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"39","issue":null,"first_page":"118","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.991599977016449,"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":0.8352994322776794},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7898538112640381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6415905952453613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5322418212890625},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5318595767021179},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.48365318775177},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.44819819927215576},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4458494782447815},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43712317943573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42304736375808716},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42040857672691345},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.24043047428131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8352994322776794},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7898538112640381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6415905952453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5322418212890625},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5318595767021179},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.48365318775177},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.44819819927215576},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4458494782447815},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43712317943573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42304736375808716},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42040857672691345},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.24043047428131104},{"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt.2014.7078560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:92449","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:arXiv.org:1509.04934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1509.04934","pdf_url":"https://arxiv.org/pdf/1509.04934","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1509.04934","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1509.04934","pdf_url":"https://arxiv.org/pdf/1509.04934","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","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":27,"referenced_works":["https://openalex.org/W943204654","https://openalex.org/W1145712207","https://openalex.org/W1514851561","https://openalex.org/W1515103638","https://openalex.org/W1524430132","https://openalex.org/W1563750459","https://openalex.org/W1576520375","https://openalex.org/W1877467042","https://openalex.org/W2016902084","https://openalex.org/W2021167307","https://openalex.org/W2037740282","https://openalex.org/W2049633694","https://openalex.org/W2051580196","https://openalex.org/W2087912899","https://openalex.org/W2090861223","https://openalex.org/W2100969003","https://openalex.org/W2118724348","https://openalex.org/W2119821739","https://openalex.org/W2130722890","https://openalex.org/W2144037622","https://openalex.org/W2155781791","https://openalex.org/W2159138759","https://openalex.org/W2407968415","https://openalex.org/W4239510810","https://openalex.org/W6633735077","https://openalex.org/W6634442568","https://openalex.org/W6682641560"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W4316036082"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,114,119],"novel":[4,170],"method":[5],"for":[6],"extracting":[7],"acoustic":[8,84],"features":[9,19,50,112,130,136,172],"that":[10,28],"characterise":[11],"the":[12,23,41,48,55,69,72,75,108,163,166,169],"background":[13,57],"environment":[14],"in":[15,54,71,86,113,118,137,177],"audio":[16,43,56],"recordings.":[17],"These":[18],"are":[20],"based":[21],"on":[22],"output":[24],"of":[25,62,68,74,83,96,110,121,151,165],"an":[26],"alignment":[27],"fits":[29],"multiple":[30],"parallel":[31],"background-based":[32],"Constrained":[33],"Maximum":[34],"Likelihood":[35],"Linear":[36,134],"Regression":[37],"transformations":[38],"asynchronously":[39],"to":[40,79,173],"input":[42],"signal.":[44],"With":[45],"this":[46,81,106,138],"setup,":[47],"resulting":[49],"can":[51],"track":[52],"changes":[53],"like":[58],"appearance":[59],"and":[60,103,158,175],"disappearance":[61],"music,":[63],"applause":[64],"or":[65,99],"laughter,":[66],"independently":[67],"speakers":[70],"foreground":[73],"audio.":[76],"The":[77,127,149],"ability":[78],"provide":[80],"type":[82],"description":[85],"audiovisual":[87],"data":[88],"has":[89],"many":[90],"potential":[91],"applications,":[92],"including":[93],"automatic":[94,101],"classification":[95],"broadcast":[97],"archives":[98],"improving":[100],"transcription":[102],"subtitling.":[104],"In":[105],"paper,":[107],"performance":[109,164],"these":[111],"genre":[115],"identification":[116],"task":[117,139],"set":[120],"332":[122],"BBC":[123],"shows":[124],"is":[125],"explored.":[126],"proposed":[128],"background-tracking":[129,171],"outperform":[131],"short-term":[132],"Perceptual":[133],"Prediction":[135],"using":[140],"Gaussian":[141],"Mixture":[142],"Model":[143],"classifiers":[144],"(62%":[145],"vs":[146],"72%":[147],"accuracy).":[148],"use":[150],"more":[152],"complex":[153],"classifiers,":[154],"Hidden":[155],"Markov":[156],"Models":[157],"Support":[159],"Vector":[160],"Machines,":[161],"increases":[162],"system":[167],"with":[168],"79%":[174],"81%":[176],"accuracy":[178],"respectively.":[179]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}