{"id":"https://openalex.org/W3005801733","doi":"https://doi.org/10.1109/icassp40776.2020.9054315","title":"Improving Automated Segmentation of Radio Shows with Audio Embeddings","display_name":"Improving Automated Segmentation of Radio Shows with Audio Embeddings","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3005801733","doi":"https://doi.org/10.1109/icassp40776.2020.9054315","mag":"3005801733"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.05194","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066006450","display_name":"Oberon Berlage","orcid":null},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Oberon Berlage","raw_affiliation_strings":["University of Amsterdam"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045757195","display_name":"Klaus-Michael Lux","orcid":"https://orcid.org/0000-0002-8930-2464"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Klaus-Michael Lux","raw_affiliation_strings":["Radboud Universiteit Nijmegen"],"affiliations":[{"raw_affiliation_string":"Radboud Universiteit Nijmegen","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012293053","display_name":"David Graus","orcid":"https://orcid.org/0000-0002-6245-0870"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Graus","raw_affiliation_strings":["FD Mediagroep"],"affiliations":[{"raw_affiliation_string":"FD Mediagroep","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066006450"],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":0.4571,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59072172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"751","last_page":"755"},"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":0.9945999979972839,"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":0.9896000027656555,"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/segmentation","display_name":"Segmentation","score":0.7945293188095093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7902110815048218},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6639779806137085},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6263250708580017},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5761253833770752},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5654215216636658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5362590551376343},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5099054574966431},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4902525246143341},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43759629130363464}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7945293188095093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902110815048218},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6639779806137085},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6263250708580017},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5761253833770752},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5654215216636658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5362590551376343},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5099054574966431},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4902525246143341},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43759629130363464},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.05194","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.05194","pdf_url":"https://arxiv.org/pdf/2002.05194","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:2002.05194","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.05194","pdf_url":"https://arxiv.org/pdf/2002.05194","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W94155879","https://openalex.org/W1626945812","https://openalex.org/W1686810756","https://openalex.org/W1828401780","https://openalex.org/W1972567154","https://openalex.org/W2017292914","https://openalex.org/W2052666245","https://openalex.org/W2059652044","https://openalex.org/W2102372132","https://openalex.org/W2140836433","https://openalex.org/W2251216540","https://openalex.org/W2252211741","https://openalex.org/W2296681920","https://openalex.org/W2402788137","https://openalex.org/W2526050071","https://openalex.org/W2550241133","https://openalex.org/W2725868244","https://openalex.org/W2758665125","https://openalex.org/W2761764495","https://openalex.org/W2777971620","https://openalex.org/W2786539019","https://openalex.org/W2803193013","https://openalex.org/W2962736743","https://openalex.org/W2962756039","https://openalex.org/W2962835968","https://openalex.org/W2963036257","https://openalex.org/W2963571336","https://openalex.org/W2996731350","https://openalex.org/W3134214488","https://openalex.org/W4232972322","https://openalex.org/W4242213453","https://openalex.org/W4293665662","https://openalex.org/W6637373629","https://openalex.org/W6638575021","https://openalex.org/W6675332481","https://openalex.org/W6691919016","https://openalex.org/W6697456849","https://openalex.org/W6713540585","https://openalex.org/W6729831399","https://openalex.org/W6740333300","https://openalex.org/W6791027380"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"Audio":[0],"features":[1],"have":[2],"been":[3],"proven":[4],"useful":[5],"for":[6,25],"increasing":[7],"the":[8,18,56],"performance":[9,54],"of":[10,21,30,55],"automated":[11],"topic":[12,52],"segmentation":[13,29,53,105],"systems.":[14],"This":[15],"study":[16],"explores":[17],"novel":[19],"task":[20,81],"using":[22,40],"audio":[23,37,57,72,100],"embeddings":[24,58,73,101],"automated,":[26],"topically":[27],"coherent":[28],"radio":[31],"shows.":[32],"We":[33,50,66],"created":[34],"three":[35,45],"different":[36,48,96],"embedding":[38],"generators":[39],"multi-class":[41],"classification":[42,80,97],"tasks":[43,98],"on":[44],"datasets":[46],"from":[47],"domains.":[49],"evaluate":[51],"and":[59],"compare":[60],"it":[61],"against":[62],"a":[63,69,76],"text-only":[64,85],"baseline.":[65],"find":[67,94],"that":[68,95,102],"set-up":[70],"including":[71],"generated":[74],"through":[75],"non-speech":[77],"sound":[78],"event":[79],"significantly":[82],"outperforms":[83],"our":[84],"baseline":[86],"by":[87],"32.3%":[88],"in":[89,104],"F1-measure.":[90],"In":[91],"addition,":[92],"we":[93],"yield":[99],"vary":[103],"performance.":[106]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}