{"id":"https://openalex.org/W2141739745","doi":"https://doi.org/10.1109/tasl.2010.2041384","title":"Segmentation, Indexing, and Retrieval for Environmental and Natural Sounds","display_name":"Segmentation, Indexing, and Retrieval for Environmental and Natural Sounds","publication_year":2010,"publication_date":"2010-02-16","ids":{"openalex":"https://openalex.org/W2141739745","doi":"https://doi.org/10.1109/tasl.2010.2041384","mag":"2141739745"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2041384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2041384","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["School of Arts, Media, and Engineering, Arizona State University, Tempe, AZ, USA","School of Arts Media and Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"School of Arts, Media, and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School of Arts Media and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006846206","display_name":"Jiachen Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiachen Xue","raw_affiliation_strings":["School of Arts, Media, and Engineering, Arizona State University, Tempe, AZ, USA","School of Arts Media and Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"School of Arts, Media, and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School of Arts Media and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062801525","display_name":"Harvey Thornburg","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harvey Thornburg","raw_affiliation_strings":["School of Arts, Media, and Engineering, Arizona State University, Tempe, AZ, USA","School of Arts Media and Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"School of Arts, Media, and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School of Arts Media and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045289726","display_name":"Brandon Mechtley","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brandon Mechtley","raw_affiliation_strings":["School of Arts, Media, and Engineering, Arizona State University, Tempe, AZ, USA","School of Arts Media and Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"School of Arts, Media, and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School of Arts Media and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074371899","display_name":"Andreas Spanias","orcid":"https://orcid.org/0000-0003-0306-9348"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Spanias","raw_affiliation_strings":["School of Arts, Media, and Engineering, Arizona State University, Tempe, AZ, USA","School of Arts Media and Engineering, Arizona State University, Tempe, AZ, USA"],"affiliations":[{"raw_affiliation_string":"School of Arts, Media, and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School of Arts Media and Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086940921"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":8.4284,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.98294644,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"18","issue":"3","first_page":"688","last_page":"707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/search-engine-indexing","display_name":"Search engine indexing","score":0.794653058052063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7292677164077759},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6520484089851379},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5969047546386719},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5241335034370422},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5190382599830627},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.45078200101852417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39497101306915283},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3590908646583557}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.794653058052063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7292677164077759},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6520484089851379},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5969047546386719},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5241335034370422},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5190382599830627},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.45078200101852417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39497101306915283},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3590908646583557},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2010.2041384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2041384","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W8319094","https://openalex.org/W131293899","https://openalex.org/W150213279","https://openalex.org/W210770835","https://openalex.org/W585519466","https://openalex.org/W1482605500","https://openalex.org/W1532956126","https://openalex.org/W1567997379","https://openalex.org/W1590216082","https://openalex.org/W1696644198","https://openalex.org/W1822987211","https://openalex.org/W1964538581","https://openalex.org/W1981822424","https://openalex.org/W1990014053","https://openalex.org/W2016089260","https://openalex.org/W2030105235","https://openalex.org/W2042797424","https://openalex.org/W2059260101","https://openalex.org/W2067128174","https://openalex.org/W2074188409","https://openalex.org/W2074870484","https://openalex.org/W2075978670","https://openalex.org/W2077611854","https://openalex.org/W2091425152","https://openalex.org/W2109606373","https://openalex.org/W2112446559","https://openalex.org/W2112968289","https://openalex.org/W2117168342","https://openalex.org/W2121996615","https://openalex.org/W2123587156","https://openalex.org/W2125838338","https://openalex.org/W2128519721","https://openalex.org/W2133824856","https://openalex.org/W2134282114","https://openalex.org/W2135934764","https://openalex.org/W2142635246","https://openalex.org/W2146664010","https://openalex.org/W2149020252","https://openalex.org/W2150322163","https://openalex.org/W2152322845","https://openalex.org/W2154332973","https://openalex.org/W2160605377","https://openalex.org/W2161219475","https://openalex.org/W2161755617","https://openalex.org/W2165874743","https://openalex.org/W2168175751","https://openalex.org/W2502276222","https://openalex.org/W2561675875","https://openalex.org/W2964368400","https://openalex.org/W3149745985","https://openalex.org/W4250499635","https://openalex.org/W4256399001","https://openalex.org/W6605236737","https://openalex.org/W6605983381","https://openalex.org/W6608545824","https://openalex.org/W6628911050","https://openalex.org/W6683713722","https://openalex.org/W6684578312","https://openalex.org/W6763868703"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W3024364549","https://openalex.org/W2097963413","https://openalex.org/W2995886640","https://openalex.org/W1591475660","https://openalex.org/W1974738623","https://openalex.org/W2157423375"],"abstract_inverted_index":{"We":[0,129],"propose":[1],"a":[2,27,72,85,111,132],"method":[3],"for":[4,55,142],"characterizing":[5],"sound":[6,43,65,119,154],"activity":[7],"in":[8,45,167],"fixed":[9],"spaces":[10,58],"through":[11],"segmentation,":[12],"indexing,":[13],"and":[14,36,151,159,171],"retrieval":[15,106,146,160],"of":[16,39,52,81,104,144],"continuous":[17],"audio":[18],"recordings.":[19],"Regarding":[20],"<i":[21,68,90],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[22,69,91],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">segmentation</i>":[23],",":[24],"we":[25,108],"present":[26],"dynamic":[28],"Bayesian":[29],"network":[30],"(DBN)":[31],"that":[32,77,84],"jointly":[33],"infers":[34],"onsets":[35],"end":[37],"times":[38],"the":[40,46,53,79,93,102,105,123,138],"most":[41],"prominent":[42],"events":[44,120],"space,":[47],"along":[48],"with":[49,59,71],"an":[50],"extension":[51],"algorithm":[54,115,147],"covering":[56],"large":[57],"distributed":[60],"microphone":[61],"arrays.":[62],"Each":[63],"segmented":[64,153],"event":[66,94],"is":[67],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">indexed</i>":[70],"hidden":[73],"Markov":[74],"model":[75],"(HMM)":[76],"models":[78],"distribution":[80],"example-based":[82],"queries":[83],"user":[86,134],"would":[87],"employ":[88],"to":[89,100,116,136,164],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">retrieve</i>":[92],"(or":[95],"similar":[96,118],"events).":[97],"In":[98],"order":[99],"increase":[101],"efficiency":[103],"search,":[107],"recursively":[109],"apply":[110],"modified":[112],"spectral":[113],"clustering":[114],"group":[117],"based":[121],"on":[122,148],"distance":[124],"between":[125],"their":[126],"corresponding":[127],"HMMs.":[128],"then":[130],"conduct":[131],"formal":[133],"study":[135],"obtain":[137],"relevancy":[139],"decisions":[140],"necessary":[141],"evaluation":[143],"our":[145,157],"both":[149,168],"automatically":[150],"manually":[152],"clips.":[155],"Furthermore,":[156],"segmentation":[158],"algorithms":[161],"are":[162],"shown":[163],"be":[165],"effective":[166],"quiet":[169],"indoor":[170],"noisy":[172],"outdoor":[173],"recording":[174],"conditions.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}