{"id":"https://openalex.org/W2404132239","doi":"https://doi.org/10.21437/interspeech.2011-670","title":"Detection of shouted speech in the presence of ambient noise","display_name":"Detection of shouted speech in the presence of ambient noise","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2404132239","doi":"https://doi.org/10.21437/interspeech.2011-670","mag":"2404132239"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-670","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jouni Pohjalainen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4396,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77105641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2621","last_page":"2624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.9958000183105469,"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":0.9175834655761719},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7276294827461243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.685278058052063},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6485671997070312},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6365318298339844},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6244905591011047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5347869396209717},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5212341547012329},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.49525704979896545},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4557400345802307},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.4341358542442322},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4272947311401367},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.27536165714263916},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07889452576637268},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.0636531412601471}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.9175834655761719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7276294827461243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685278058052063},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6485671997070312},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6365318298339844},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6244905591011047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5347869396209717},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5212341547012329},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.49525704979896545},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4557400345802307},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.4341358542442322},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4272947311401367},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27536165714263916},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07889452576637268},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0636531412601471},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-670","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W88864901","https://openalex.org/W119556667","https://openalex.org/W1966264494","https://openalex.org/W2096672501","https://openalex.org/W2097450352","https://openalex.org/W2122051577","https://openalex.org/W2135131618","https://openalex.org/W2135342008","https://openalex.org/W2165880886","https://openalex.org/W2170068989"],"related_works":["https://openalex.org/W2048014685","https://openalex.org/W2370972896","https://openalex.org/W2986378528","https://openalex.org/W3178345791","https://openalex.org/W1550854977","https://openalex.org/W2092661960","https://openalex.org/W4231055618","https://openalex.org/W2949211747","https://openalex.org/W3005742472","https://openalex.org/W2162441712"],"abstract_inverted_index":{"This":[0],"study":[1],"focuses":[2],"on":[3,17],"the":[4,37,54],"detection":[5],"of":[6,36],"shouted":[7],"speech":[8],"in":[9],"realistic":[10],"noisy":[11],"conditions.":[12],"An":[13],"automatic":[14,38,55],"system":[15,39,56],"based":[16],"modified":[18],"mel":[19],"frequency":[20],"cepstral":[21],"coefficient":[22],"(MFCC)":[23],"feature":[24],"extraction":[25],"and":[26],"Gaussian":[27],"mixture":[28],"model":[29],"(GMM)":[30],"classification":[31,62],"is":[32,40,65],"developed.":[33],"The":[34],"performance":[35],"compared":[41],"against":[42],"human":[43],"perception":[44],"measured":[45],"by":[46,63],"a":[47],"listening":[48],"test.":[49],"At":[50],"moderate":[51],"noise":[52],"levels,":[53],"outperforms":[57],"humans.":[58],"In":[59],"severe":[60],"conditions,":[61],"humans":[64],"clearly":[66],"better.":[67]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
