{"id":"https://openalex.org/W2135095563","doi":"https://doi.org/10.1109/icassp.2005.1415163","title":"Variational Bayesian Feature Saliency for Audio Type Classification","display_name":"Variational Bayesian Feature Saliency for Audio Type Classification","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2135095563","doi":"https://doi.org/10.1109/icassp.2005.1415163","mag":"2135095563"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5061495800","display_name":"Fabio Valente","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"F. Valente","raw_affiliation_strings":["Institut Eurecom, Sophia-Antipolis, France","[Institute Eurecom,   Sophia Antipolis, France]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Eurecom, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"[Institute Eurecom,   Sophia Antipolis, France]","institution_ids":["https://openalex.org/I1902872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108525230","display_name":"C. Wellekens","orcid":null},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Wellekens","raw_affiliation_strings":["Institut Eurecom, Sophia-Antipolis, France","[Institute Eurecom,   Sophia Antipolis, France]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Eurecom, Sophia-Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"[Institute Eurecom,   Sophia Antipolis, France]","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18763202,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"513","last_page":"516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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":0.9954000115394592,"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":0.9941999912261963,"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/discriminative-model","display_name":"Discriminative model","score":0.7480745315551758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7057042121887207},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6404874324798584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6011697053909302},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5969533920288086},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5943342447280884},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.49028661847114563},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.48753878474235535},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41318345069885254},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4121685028076172}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7480745315551758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7057042121887207},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6404874324798584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011697053909302},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5969533920288086},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5943342447280884},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.49028661847114563},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.48753878474235535},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41318345069885254},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4121685028076172},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2016243284","https://openalex.org/W2063415950","https://openalex.org/W2100030705","https://openalex.org/W2143990842","https://openalex.org/W2147830002","https://openalex.org/W2152321560","https://openalex.org/W2172085063","https://openalex.org/W2399255709","https://openalex.org/W2567948266","https://openalex.org/W6681800702","https://openalex.org/W6712478597","https://openalex.org/W6731548788"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W4205463238","https://openalex.org/W259157601","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374","https://openalex.org/W2146591867"],"abstract_inverted_index":{"An":[0],"approach":[1],"based":[2,28],"on":[3,83],"variational":[4],"Bayesian":[5],"feature":[6,39],"saliency":[7,40,73],"(VBFS)":[8],"for":[9,41,74],"robust":[10],"audio":[11,43,76],"type":[12],"classification":[13],"is":[14,32,63],"proposed.":[15],"VBFS":[16,31],"aims":[17],"at":[18],"finding":[19],"the":[20],"most":[21],"discriminative":[22],"features":[23],"in":[24,55,66],"Gaussian":[25],"mixture":[26],"model":[27,60],"recognition":[29],"systems.":[30],"applied":[33],"to":[34,57],"capture":[35],"inter-type":[36],"and":[37],"intra-type":[38],"different":[42,75],"types":[44,77],"(music,":[45],"background":[46],"noise,":[47],"wide":[48],"band":[49,52],"speech,":[50,53],"narrow":[51],"etc.)":[54],"order":[56],"increase":[58],"a":[59],"generality":[61],"that":[62,71],"always":[64],"poor":[65],"non-speech":[67],"models.":[68],"We":[69],"show":[70],"inferring":[72],"improves":[78],"classifications.":[79],"Experiments":[80],"are":[81],"run":[82],"broadcast":[84],"news":[85],"1996-Hub4.":[86]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}