{"id":"https://openalex.org/W2089975605","doi":"https://doi.org/10.1109/ispacs.2013.6704522","title":"Model-based speech/non-speech segmentation of a heterogeneous multilingual TV broadcast collection","display_name":"Model-based speech/non-speech segmentation of a heterogeneous multilingual TV broadcast collection","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2089975605","doi":"https://doi.org/10.1109/ispacs.2013.6704522","mag":"2089975605"},"language":"en","primary_location":{"id":"doi:10.1109/ispacs.2013.6704522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs.2013.6704522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 International Symposium on Intelligent Signal Processing and Communication Systems","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/A5032699386","display_name":"Brecht Desplanques","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Brecht Desplanques","raw_affiliation_strings":["ELlS Multimedia Lab, Ghent University-iMinds, Ghent, Belgium","ELIS Multimedia Lab., Ghent Univ. - iMinds, Ghent, Belgium"],"affiliations":[{"raw_affiliation_string":"ELlS Multimedia Lab, Ghent University-iMinds, Ghent, Belgium","institution_ids":["https://openalex.org/I39327780","https://openalex.org/I32597200"]},{"raw_affiliation_string":"ELIS Multimedia Lab., Ghent Univ. - iMinds, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109810030","display_name":"Jean\u2010Pierre Martens","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jean-Pierre Martens","raw_affiliation_strings":["ELlS Multimedia Lab, Ghent University-iMinds, Ghent, Belgium","ELIS Multimedia Lab., Ghent Univ. - iMinds, Ghent, Belgium"],"affiliations":[{"raw_affiliation_string":"ELlS Multimedia Lab, Ghent University-iMinds, Ghent, Belgium","institution_ids":["https://openalex.org/I39327780","https://openalex.org/I32597200"]},{"raw_affiliation_string":"ELIS Multimedia Lab., Ghent Univ. - iMinds, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032699386"],"corresponding_institution_ids":["https://openalex.org/I32597200","https://openalex.org/I39327780"],"apc_list":null,"apc_paid":null,"fwci":0.6384,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69848893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"55","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":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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.8589217662811279},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7215622067451477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6559707522392273},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6162208914756775},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.535233199596405},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5339139103889465},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5086511373519897},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46585044264793396},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.44394388794898987},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43228596448898315},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.43089836835861206},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42399200797080994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4142882525920868},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.20584815740585327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8589217662811279},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7215622067451477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6559707522392273},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6162208914756775},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.535233199596405},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5339139103889465},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5086511373519897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46585044264793396},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.44394388794898987},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43228596448898315},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.43089836835861206},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42399200797080994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4142882525920868},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.20584815740585327},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ispacs.2013.6704522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispacs.2013.6704522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 International Symposium on Intelligent Signal Processing and Communication Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:4315775","is_oa":false,"landing_page_url":"https://biblio.ugent.be/publication/4315775","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781467363600","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W3765491","https://openalex.org/W16074020","https://openalex.org/W83866820","https://openalex.org/W84258004","https://openalex.org/W97107628","https://openalex.org/W165453733","https://openalex.org/W1537738516","https://openalex.org/W1547083988","https://openalex.org/W1988540447","https://openalex.org/W2005027770","https://openalex.org/W2074394031","https://openalex.org/W2146194791","https://openalex.org/W2159591770","https://openalex.org/W2407232104","https://openalex.org/W4285719527","https://openalex.org/W6600154122","https://openalex.org/W6600661334","https://openalex.org/W6603443942","https://openalex.org/W6604007911","https://openalex.org/W6606651766","https://openalex.org/W6632230212","https://openalex.org/W6632910081","https://openalex.org/W6713616624"],"related_works":["https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W4388404911","https://openalex.org/W1987021544","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W3151376046","https://openalex.org/W2964829415","https://openalex.org/W2341426843","https://openalex.org/W2009814707"],"abstract_inverted_index":{"Multimedia":[0],"Information":[1],"Retrieval":[2],"systems":[3],"normally":[4],"comprise":[5],"a":[6,10,22,33,52,66,72,111,124,141,147],"preprocessor":[7],"that":[8,31,38,56,88,132],"performs":[9],"speech/non-speech":[11],"(SNS)":[12],"segmentation":[13,23],"of":[14,20,45,76,114,137,150,167],"the":[15,27,89,101,134,138,151,157,168,176],"audio":[16,28],"stream.":[17],"The":[18],"goal":[19],"such":[21,97],"is":[24,63,130],"to":[25,119,182],"divide":[26],"into":[29],"intervals":[30,37],"need":[32,40],"lexical":[34],"transcription":[35],"and":[36,70,110,145,165],"just":[39],"some":[41],"categorization":[42],"in":[43],"terms":[44],"jingle,":[46],"applause,":[47],"etc.":[48,85],"In":[49],"this":[50],"paper":[51],"baseline":[53],"SNS":[54,126],"system":[55,90],"was":[57],"trained":[58],"on":[59,65,71,175],"monolingual":[60],"BN":[61,68],"data":[62],"evaluated":[64],"multilingual":[67],"corpus":[69],"heterogeneous":[73,102],"corpus,":[74,103],"composed":[75],"diverse":[77],"TV":[78],"shows":[79],"including":[80],"discussions,":[81],"soaps,":[82],"animation":[83],"films,":[84],"It":[86],"appears":[87],"exhibits":[91],"serious":[92],"deficiencies":[93],"when":[94],"confronted":[95],"with":[96],"out-of-domain":[98],"data.":[99],"Especially":[100],"characterized":[104],"by":[105],"many":[106],"short":[107],"speaker":[108,172],"turns":[109,117],"rich":[112],"pallet":[113],"non-speech":[115],"intervals,":[116],"out":[118],"be":[120],"challenging.":[121],"However,":[122],"employing":[123],"proper":[125],"information":[127],"criterion,":[128],"it":[129],"demonstrated":[131],"enhancing":[133],"acoustic":[135,152],"representation":[136],"audio,":[139],"creating":[140],"richer":[142],"music":[143],"model":[144],"performing":[146],"file-wise":[148],"adaptation":[149],"models":[153],"can":[154],"significantly":[155],"increase":[156],"performance.":[158],"Complex":[159],"architectures":[160],"permitting":[161],"explicit":[162],"duration":[163],"modeling":[164],"re-segmentation":[166],"speech":[169],"parts":[170],"after":[171],"change":[173],"detection":[174],"other":[177],"hand":[178],"do":[179],"not":[180],"seem":[181],"help.":[183]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
