{"id":"https://openalex.org/W2294701319","doi":"https://doi.org/10.21437/interspeech.2013-535","title":"A blind segmentation approach to acoustic event detection based on i-vector","display_name":"A blind segmentation approach to acoustic event detection based on i-vector","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2294701319","doi":"https://doi.org/10.21437/interspeech.2013-535","mag":"2294701319"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-535","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5101472289","display_name":"Zhen Huang","orcid":"https://orcid.org/0000-0002-1772-7674"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhen Huang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109257481","display_name":"You-Chi Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You-Chi Cheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012954193","display_name":"Kehuang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kehuang Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ville Hautam\u00e4ki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101472289"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.143,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.9603321,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2282","last_page":"2286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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":0.9945999979972839,"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/robustness","display_name":"Robustness (evolution)","score":0.740710437297821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.716590404510498},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6386605501174927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6363058686256409},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6149324774742126},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5984176397323608},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5941362380981445},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4735794961452484},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.47064703702926636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44937658309936523},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33330845832824707}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.740710437297821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.716590404510498},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6386605501174927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6363058686256409},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6149324774742126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5984176397323608},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5941362380981445},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4735794961452484},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.47064703702926636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44937658309936523},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33330845832824707},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2013-535","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.646.4421","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.4421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.joensuu.fi/~villeh/IS130143.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W111477576","https://openalex.org/W1663973292","https://openalex.org/W2049633694","https://openalex.org/W2052384514","https://openalex.org/W2106284094","https://openalex.org/W2107638917","https://openalex.org/W2115447976","https://openalex.org/W2119821739","https://openalex.org/W2120929742","https://openalex.org/W2121415728","https://openalex.org/W2123172924","https://openalex.org/W2124000984","https://openalex.org/W2125027820","https://openalex.org/W2125838338","https://openalex.org/W2129634963","https://openalex.org/W2133138903","https://openalex.org/W2150769028","https://openalex.org/W2151484683","https://openalex.org/W2153635508","https://openalex.org/W2158182274","https://openalex.org/W2158762315","https://openalex.org/W2167295232","https://openalex.org/W2170989130","https://openalex.org/W2183164523","https://openalex.org/W2184512081","https://openalex.org/W2187725594","https://openalex.org/W2395750323","https://openalex.org/W2404921859","https://openalex.org/W2406257467","https://openalex.org/W2429638696","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2025614924","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W1974738623","https://openalex.org/W2157423375","https://openalex.org/W1522196789"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"new":[3],"blind":[4,142],"segmentation":[5],"approach":[6],"to":[7,17,118],"acous-tic":[8],"event":[9,59,139],"detection":[10],"(AED)":[11],"based":[12,76,104],"on":[13,79],"i-vectors.":[14],"Conventional":[15],"approaches":[16],"AED":[18],"often":[19],"required":[20],"well-segmented":[21],"data":[22,84],"with":[23,53,57,88],"non-overlapping":[24],"boundaries":[25],"for":[26,64],"competing":[27],"events.":[28],"Inspired":[29],"by":[30,128],"block-based":[31],"automatic":[32],"image":[33,36],"annotation":[34],"in":[35,96,122],"retrieval":[37],"tasks,":[38],"we":[39],"blindly":[40],"segment":[41],"audio":[42,83],"streams":[43],"into":[44],"equal-length":[45],"pieces,":[46],"label":[47],"the":[48,99,119,123,129,133],"underlying":[49],"observed":[50],"acoustic":[51,134,138],"events":[52],"mul-tiple":[54],"categories":[55],"and":[56,66,73],"no":[58],"boundary":[60],"information,":[61],"extract":[62],"i-vector":[63,130],"them,":[65],"perform":[67],"classification":[68],"using":[69],"support":[70,144],"vec-tor":[71],"machine":[72],"maximal":[74,147],"figure-of-merit":[75,148],"classifiers.":[77],"Ex-periments":[78],"various":[80],"sets":[81],"of":[82,91,132],"show":[85],"promising":[86],"results":[87],"an":[89],"average":[90],"8":[92],"%":[93],"absolute":[94],"gain":[95],"F1":[97],"over":[98],"conventional":[100],"hidden":[101],"Markov":[102],"model":[103],"approach.":[105],"An":[106],"enhanced":[107,124],"robustness":[108],"at":[109],"different":[110],"noise":[111],"levels":[112],"is":[113],"also":[114],"observed.":[115],"The":[116],"key":[117],"suc-cess":[120],"lies":[121],"discrimination":[125],"power":[126],"offered":[127],"representation":[131],"data.":[135],"Index":[136],"Terms:":[137],"detection,":[140],"i-vector,":[141],"segmen-tation,":[143],"vector":[145],"machine,":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}