{"id":"https://openalex.org/W2096672501","doi":"https://doi.org/10.1109/icassp.2011.5947471","title":"Shout detection in noise","display_name":"Shout detection in noise","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2096672501","doi":"https://doi.org/10.1109/icassp.2011.5947471","mag":"2096672501"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5008322847","display_name":"Jouni Pohjalainen","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jouni Pohjalainen","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","Aalto University, Department of Signal Processing and Acoustics, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University, Department of Signal Processing and Acoustics, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","Aalto University, Department of Signal Processing and Acoustics, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Aalto University, Department of Signal Processing and Acoustics, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Joensuu, Finland","University of Eastern Finland, School of Computing, Joensuu, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]},{"raw_affiliation_string":"University of Eastern Finland, School of Computing, Joensuu, Finland","institution_ids":["https://openalex.org/I175532246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6379,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.90824801,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4968","last_page":"4971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9919000267982483,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.9423664808273315},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.724571943283081},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6828001737594604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6500495672225952},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6168429851531982},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5857344269752502},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5234270095825195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5170653462409973},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.4961796700954437},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.47438862919807434},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47359994053840637},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.43754279613494873},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4332996606826782},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14149057865142822},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09936967492103577}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.9423664808273315},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724571943283081},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6828001737594604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6500495672225952},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6168429851531982},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5857344269752502},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5234270095825195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5170653462409973},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.4961796700954437},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.47438862919807434},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47359994053840637},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.43754279613494873},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4332996606826782},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14149057865142822},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09936967492103577},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947471","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.220.9882","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.220.9882","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/pages/tkinnu/webpage/pdf/ICASSP2011_shout.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W5438179","https://openalex.org/W88864901","https://openalex.org/W1966264494","https://openalex.org/W2025386793","https://openalex.org/W2043527182","https://openalex.org/W2097450352","https://openalex.org/W2103279261","https://openalex.org/W2122051577","https://openalex.org/W2125838338","https://openalex.org/W2135027063","https://openalex.org/W2135131618","https://openalex.org/W2135342008","https://openalex.org/W2159018645","https://openalex.org/W2165880886","https://openalex.org/W2166223208","https://openalex.org/W2170068989","https://openalex.org/W6600220327","https://openalex.org/W6680104056","https://openalex.org/W6683486567"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2372625757","https://openalex.org/W4313178214","https://openalex.org/W2048014685","https://openalex.org/W3009295899","https://openalex.org/W2370972896","https://openalex.org/W2075383893","https://openalex.org/W2368689451","https://openalex.org/W2040882540"],"abstract_inverted_index":{"For":[0],"the":[1,55,63,71,77,86,120],"task":[2],"of":[3,38,49,54],"detecting":[4],"shouted":[5],"speech":[6,41],"in":[7],"a":[8,14,106,110],"noisy":[9],"environment,":[10],"this":[11],"paper":[12],"introduces":[13],"system":[15,58],"based":[16],"on":[17],"mel":[18],"frequency":[19],"cepstral":[20],"coefficient":[21],"(MFCC)":[22],"feature":[23,65,72,83],"extraction,":[24],"unsupervised":[25],"frame":[26],"dropping":[27],"and":[28,42,75],"Gaussian":[29],"mixture":[30],"model":[31],"(GMM)":[32],"classification.":[33],"The":[34,52],"evaluation":[35],"material":[36],"consists":[37],"phonemically":[39],"identical":[40],"shouting":[43],"as":[44,46],"well":[45],"environmental":[47],"noise":[48],"varying":[50,62],"levels.":[51],"performance":[53,88],"shout":[56],"detection":[57],"is":[59,89,96,100],"analyzed":[60],"by":[61],"MFCC":[64,93],"extraction":[66],"with":[67,115],"respect":[68],"to":[69],"1)":[70],"vector":[73,84],"length":[74],"2)":[76],"spectrum":[78,104,113],"estimation":[79],"method.":[80],"As":[81],"for":[82],"length,":[85],"best":[87],"obtained":[90],"using":[91],"30":[92],"coefficients,":[94],"which":[95],"more":[97],"than":[98],"what":[99],"conventionally":[101],"used.":[102],"In":[103],"estimation,":[105],"scheme":[107],"that":[108],"combines":[109],"linear":[111],"prediction":[112],"envelope":[114],"spectral":[116],"fine":[117],"structure":[118],"outperforms":[119],"conventional":[121],"FFT.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
