{"id":"https://openalex.org/W2156043751","doi":null,"title":"A scanning window scheme based on SVM training error rate for unsupervised audio segmentation","display_name":"A scanning window scheme based on SVM training error rate for unsupervised audio segmentation","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W2156043751","mag":"2156043751"},"language":"en","primary_location":{"id":"mag:2156043751","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/eusipco/eusipco2010.html#SadjadiH10","pdf_url":null,"source":{"id":"https://openalex.org/S4363607788","display_name":"European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"European Signal Processing Conference","raw_type":null},"volume":null,"type":"conference-paper","indexed_in":[],"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/A5051167459","display_name":"Seyed Omid Sadjadi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyed Omid Sadjadi","raw_affiliation_strings":["The Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, The University of Texas at Dallas, 800 West Campbell Road, Richardson, TX 75080-3021, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, The University of Texas at Dallas, 800 West Campbell Road, Richardson, TX 75080-3021, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["The Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, The University of Texas at Dallas, 800 West Campbell Road, Richardson, TX 75080-3021, USA"],"raw_orcid":"https://orcid.org/0000-0003-1382-9929","affiliations":[{"raw_affiliation_string":"The Center for Robust Speech Systems (CRSS), Department of Electrical Engineering, The University of Texas at Dallas, 800 West Campbell Road, Richardson, TX 75080-3021, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.367,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56289121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1262","last_page":"1266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9814000129699707,"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":0.9814000129699707,"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":0.00930000003427267,"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":0.007699999958276749,"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/audio-segmentation","display_name":"audio segmentation","score":0.7720000147819519},{"id":"https://openalex.org/keywords/unsupervised-segmentation","display_name":"unsupervised segmentation","score":0.9150000214576721},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.8009999990463257},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.722000002861023},{"id":"https://openalex.org/keywords/generalized-likelihood-ratio","display_name":"generalized likelihood ratio","score":0.9380000233650208},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.9750000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7879620790481567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7263518571853638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6796024441719055},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6472287774085999},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.634499728679657},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.6090471744537354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5322888493537903},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5030187964439392},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.46437138319015503},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.43728041648864746},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43338465690612793},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.28012514114379883}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2156043751","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/eusipco/eusipco2010.html#SadjadiH10","pdf_url":null,"source":{"id":"https://openalex.org/S4363607788","display_name":"European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"European Signal Processing Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W1482605500","https://openalex.org/W1563088657","https://openalex.org/W1827418370","https://openalex.org/W2044591814","https://openalex.org/W2106055371","https://openalex.org/W2109240172","https://openalex.org/W2115713555","https://openalex.org/W2121127941","https://openalex.org/W2128838222","https://openalex.org/W2137197207","https://openalex.org/W2143728216","https://openalex.org/W2153557299","https://openalex.org/W2155691655","https://openalex.org/W2159237780","https://openalex.org/W2405439032","https://openalex.org/W2541212214"],"related_works":["https://openalex.org/W2136450786","https://openalex.org/W2121127941","https://openalex.org/W1575729891","https://openalex.org/W2172081649","https://openalex.org/W2096520398","https://openalex.org/W2390789328","https://openalex.org/W2143728216","https://openalex.org/W7097119770","https://openalex.org/W2083837083","https://openalex.org/W2153557299"],"abstract_inverted_index":{"Audio":[0],"segmentation":[1,44,64,95],"has":[2],"applications":[3],"in":[4,23,77,114],"a":[5,20,34],"variety":[6],"of":[7,54,87,118],"contexts,":[8],"such":[9],"as":[10,19,33],"automatic":[11,24],"broadcast":[12],"news":[13],"transcription,":[14],"audio":[15,42,63,88,116],"information":[16,100],"retrieval,":[17],"and":[18,45,59,107],"pre-processing":[21],"step":[22],"speech":[25],"recognition":[26],"(ASR).":[27],"The":[28,73],"Support":[29],"vector":[30],"machine":[31],"(SVM),":[32],"binary":[35],"classifier,":[36],"is":[37,75],"commonly":[38],"used":[39],"for":[40],"supervised":[41],"signal":[43],"classification.":[46],"In":[47],"this":[48],"study,":[49],"inspired":[50],"by":[51],"the":[52,68,78,94],"idea":[53],"scanning":[55],"window,":[56],"we":[57],"present":[58],"evaluate":[60],"an":[61],"unsupervised":[62,76],"approach":[65,74],"based":[66],"on":[67],"SVM":[69],"training":[70],"error":[71],"rate.":[72],"sense":[79],"that":[80,93],"it":[81],"does":[82],"not":[83],"require":[84],"prior":[85],"knowledge":[86],"classes.":[89],"Experimental":[90],"results":[91],"indicate":[92],"technique":[96],"outperforms":[97],"traditional":[98],"Bayesian":[99],"criterion":[101],"(BIC),":[102],"generalized":[103],"likelihood":[104],"ratio":[105],"(GLR),":[106],"Gaussian":[108],"mixture":[109],"models":[110],"(GMM)":[111],"methods,":[112],"particularly":[113],"detecting":[115],"landmarks":[117],"short":[119],"duration.":[120]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}