{"id":"https://openalex.org/W2123843894","doi":"https://doi.org/10.1186/1687-4722-2013-1","title":"Context-dependent sound event detection","display_name":"Context-dependent sound event detection","publication_year":2013,"publication_date":"2013-01-09","ids":{"openalex":"https://openalex.org/W2123843894","doi":"https://doi.org/10.1186/1687-4722-2013-1","mag":"2123843894"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2013-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2013-1","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2013-1","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2013-1","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059929826","display_name":"Toni Heittola","orcid":"https://orcid.org/0000-0002-8855-0415"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Toni Heittola","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, Finland","[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, Finland","[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076376566","display_name":"Antti Eronen","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Antti Eronen","raw_affiliation_strings":["Nokia Research Center, Tampere, Visiokatu 3, Finland","Nokia Res. Center, Tampere, Finland#TAB#"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Tampere, Visiokatu 3, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Res. Center, Tampere, Finland#TAB#","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, Finland","[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, P.O. Box 553, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"[Department of Signal Processing, Tampere University of Technology, Tampere, FINLAND]","institution_ids":["https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059929826"],"corresponding_institution_ids":["https://openalex.org/I4210133110"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":15.8613,"has_fulltext":true,"cited_by_count":216,"citation_normalized_percentile":{"value":0.99462893,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"2013","issue":"1","first_page":null,"last_page":null},"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":0.9995999932289124,"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":0.9970999956130981,"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/event","display_name":"Event (particle physics)","score":0.7602126598358154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7030587196350098},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6859537363052368},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.629603385925293},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5963917970657349},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.568930447101593},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5537058711051941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4252779483795166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3931899964809418},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22779279947280884},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.18740731477737427}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7602126598358154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7030587196350098},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6859537363052368},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.629603385925293},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5963917970657349},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.568930447101593},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5537058711051941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4252779483795166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3931899964809418},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22779279947280884},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.18740731477737427},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/1687-4722-2013-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2013-1","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2013-1","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2013-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2013-1","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2013-1","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2123843894.pdf","grobid_xml":"https://content.openalex.org/works/W2123843894.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W423095831","https://openalex.org/W1533561824","https://openalex.org/W1605026219","https://openalex.org/W1622490909","https://openalex.org/W1677236997","https://openalex.org/W1766693173","https://openalex.org/W1786709202","https://openalex.org/W1822987211","https://openalex.org/W1967661515","https://openalex.org/W1985925461","https://openalex.org/W2019432531","https://openalex.org/W2026754475","https://openalex.org/W2048174296","https://openalex.org/W2085663684","https://openalex.org/W2086468861","https://openalex.org/W2089368853","https://openalex.org/W2094709280","https://openalex.org/W2104112890","https://openalex.org/W2114777924","https://openalex.org/W2115447976","https://openalex.org/W2118230268","https://openalex.org/W2125838338","https://openalex.org/W2126109423","https://openalex.org/W2126921622","https://openalex.org/W2130640900","https://openalex.org/W2132317325","https://openalex.org/W2137343183","https://openalex.org/W2141328672","https://openalex.org/W2141739745","https://openalex.org/W2142384583","https://openalex.org/W2153220212","https://openalex.org/W2156481234","https://openalex.org/W2159564241","https://openalex.org/W2160335114","https://openalex.org/W2160849440","https://openalex.org/W2160860215","https://openalex.org/W2165880886","https://openalex.org/W2188041026","https://openalex.org/W2327970305","https://openalex.org/W2331166300","https://openalex.org/W2497516627","https://openalex.org/W2561557072","https://openalex.org/W2595741664","https://openalex.org/W2913524657","https://openalex.org/W3021396111","https://openalex.org/W3150354321","https://openalex.org/W4205947759","https://openalex.org/W4231293494","https://openalex.org/W4233392025","https://openalex.org/W4236837445","https://openalex.org/W4244238878","https://openalex.org/W4255686019","https://openalex.org/W4256399001","https://openalex.org/W4285719527","https://openalex.org/W4365806309"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1521297879","https://openalex.org/W2036150633","https://openalex.org/W3184123547","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W2536059291"],"abstract_inverted_index":{"The":[0,68,135,179,241],"work":[1],"presented":[2],"in":[3,14,61],"this":[4],"article":[5],"studies":[6],"how":[7,22],"the":[8,15,23,42,51,62,104,110,117,130,156,167,209,221,232,235,248,253,258,260,269],"context":[9,34,59,77,108],"information":[10,35,60],"can":[11,26,263],"be":[12,264],"used":[13],"automatic":[16,63,76],"sound":[17,43,64,81,93,124,131,170,195,210],"event":[18,65,82,125,132,136,146,150,161,171,189,211,272],"detection":[19,24,66,83,133,137,151,212,222,238,261],"process,":[20],"and":[21,45,80,92,144,224],"system":[25],"benefit":[27],"from":[28],"such":[29],"information.":[30],"Humans":[31],"are":[32,86,95,153],"using":[33,88,97,176,197,268],"to":[36,207,246,252],"make":[37],"more":[38],"accurate":[39],"predictions":[40],"about":[41],"events":[44,49,94,196],"ruling":[46],"out":[47],"unlikely":[48],"given":[50],"context.":[52],"We":[53],"propose":[54],"a":[55,120,159,183],"similar":[56],"utilization":[57],"of":[58,73,109,123,217,234,237],"process.":[67],"proposed":[69,270],"approach":[70,181,243],"is":[71,113,127,163,205],"composed":[72],"two":[74],"stages:":[75],"recognition":[78],"stage":[79,138],"stage.":[84,134],"Contexts":[85],"modeled":[87,96],"Gaussian":[89],"mixture":[90],"models":[91,143],"three-state":[98],"left-to-right":[99],"hidden":[100],"Markov":[101],"models.":[102],"In":[103,155,257],"first":[105,157],"stage,":[106],"audio":[107],"tested":[111],"signal":[112],"recognized.":[114],"Based":[115],"on":[116],"recognized":[118],"context,":[119],"context-specific":[121],"set":[122],"classes":[126],"selected":[128],"for":[129,186],"also":[139],"uses":[140],"context-dependent":[141,271],"acoustic":[142],"count-based":[145],"priors.":[147],"Two":[148],"alternative":[149],"approaches":[152],"studied.":[154],"one,":[158],"monophonic":[160],"sequence":[162,190],"outputted":[164],"by":[165,191,267],"detecting":[166,192],"most":[168],"prominent":[169],"at":[172],"each":[173],"time":[174],"instance":[175],"Viterbi":[177,200],"decoding.":[178],"second":[180],"introduces":[182],"new":[184,203],"method":[185],"producing":[187],"polyphonic":[188],"multiple":[193,198],"overlapping":[194],"restricted":[199],"passes.":[201],"A":[202],"metric":[204],"introduced":[206],"evaluate":[208],"performance":[213,236],"with":[214],"various":[215],"level":[216],"polyphony.":[218],"This":[219],"combines":[220],"accuracy":[223,262],"coarse":[225],"time-resolution":[226],"error":[227],"into":[228],"one":[229],"metric,":[230],"making":[231],"comparison":[233],"algorithms":[239],"simpler.":[240],"two-step":[242],"was":[244],"found":[245],"improve":[247],"results":[249],"substantially":[250],"compared":[251],"context-independent":[254],"baseline":[255],"system.":[256],"block-level,":[259],"almost":[265],"doubled":[266],"detection.":[273]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}