{"id":"https://openalex.org/W1974094094","doi":"https://doi.org/10.1109/iscslp.2014.6936651","title":"Spectral patch based sparse coding for acoustic event detection","display_name":"Spectral patch based sparse coding for acoustic event detection","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W1974094094","doi":"https://doi.org/10.1109/iscslp.2014.6936651","mag":"1974094094"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","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/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","National institute of information and communications technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National institute of information and communications technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I29955533","display_name":"Center for Information Technology","ror":"https://ror.org/03jh5a977","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I29955533"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academic Sinica","Research Center for Information Technology Innovation, Academic Sinica, Japan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academic Sinica","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academic Sinica, Japan","institution_ids":["https://openalex.org/I29955533"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101486855","display_name":"Peng Shen","orcid":"https://orcid.org/0000-0002-0137-2629"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Peng Shen","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","National institute of information and communications technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National institute of information and communications technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001601327","display_name":"Chiori Hori","orcid":"https://orcid.org/0000-0002-4201-7578"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chiori Hori","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","National institute of information and communications technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National institute of information and communications technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034792613"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.05016401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"317","last_page":"320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T11447","display_name":"Blind Source Separation Techniques","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/sparse-approximation","display_name":"Sparse approximation","score":0.6987234354019165},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6932724118232727},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6908658742904663},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.688044011592865},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.6195436716079712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5825707912445068},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5391507744789124},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5326969623565674},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5149500966072083},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4813031256198883},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44284167885780334}],"concepts":[{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.6987234354019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6932724118232727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6908658742904663},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.688044011592865},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.6195436716079712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5825707912445068},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5391507744789124},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5326969623565674},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5149500966072083},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4813031256198883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44284167885780334},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1565317727","https://openalex.org/W1945356021","https://openalex.org/W2005876975","https://openalex.org/W2008415856","https://openalex.org/W2052711563","https://openalex.org/W2115447976","https://openalex.org/W2118585731","https://openalex.org/W2118858186","https://openalex.org/W2123843894","https://openalex.org/W2160547390","https://openalex.org/W2171680721","https://openalex.org/W2294701319","https://openalex.org/W2405774341","https://openalex.org/W6677656871","https://openalex.org/W6677919164"],"related_works":["https://openalex.org/W2890544631","https://openalex.org/W2067062989","https://openalex.org/W4205656132","https://openalex.org/W3004790527","https://openalex.org/W2111634407","https://openalex.org/W2783282829","https://openalex.org/W2579633471","https://openalex.org/W2539392819","https://openalex.org/W2203155458","https://openalex.org/W212310357"],"abstract_inverted_index":{"In":[0,73,94],"most":[1],"algorithms":[2],"for":[3,51,138],"acoustic":[4,10,15,64,92],"event":[5],"detection":[6],"(AED),":[7],"frame":[8],"based":[9,61,81,148],"representations":[11],"are":[12],"used":[13],"in":[14,23,109,160],"modeling.":[16,32,161],"Due":[17],"to":[18,42],"lack":[19],"of":[20,49,67,70,85,114],"context":[21,44,158],"information":[22,45,159],"feature":[24,37,58,78,101,137],"representation,":[25],"large":[26],"model":[27],"confusions":[28],"may":[29],"occur":[30],"during":[31],"We":[33],"have":[34],"proposed":[35],"a":[36,56,68,83,122],"learning":[38],"and":[39,91],"representation":[40,116,150],"algorithm":[41],"explore":[43],"from":[46],"temporal-frequency":[47,157],"patches":[48],"signal":[50,90,110],"AED.":[52,139],"With":[53],"the":[54,77,99,115,134,145,153],"algorithm,":[55,76],"sparse":[57,100,136,149],"was":[59,79,131],"extracted":[60,135],"on":[62,82,133],"an":[63],"dictionary":[65],"composed":[66],"bag":[69],"spectral":[71,146],"patches.":[72],"our":[74],"previous":[75],"obtained":[80],"definition":[84],"Euclidian":[86],"distance":[87],"between":[88],"input":[89],"dictionary.":[93],"this":[95],"study,":[96],"we":[97],"formulate":[98],"extraction":[102],"as":[103],"l":[104],"<sub":[105],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[106],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[107],"regularization":[108,123],"reconstruction.":[111],"The":[112],"sparsity":[113],"is":[117],"efficiently":[118],"controlled":[119],"via":[120],"varying":[121],"parameter.":[124],"A":[125],"support":[126],"vector":[127],"machine":[128],"(SVM)":[129],"classifier":[130],"built":[132],"Our":[140],"experimental":[141],"results":[142],"showed":[143],"that":[144],"patch":[147],"effectively":[151],"improved":[152],"performance":[154],"by":[155],"incorporating":[156]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}