{"id":"https://openalex.org/W1997810056","doi":"https://doi.org/10.1109/icassp.2010.5496244","title":"Modulation-based detection of speech in real background noise: Generalization to novel background classes","display_name":"Modulation-based detection of speech in real background noise: Generalization to novel background classes","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W1997810056","doi":"https://doi.org/10.1109/icassp.2010.5496244","mag":"1997810056"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5496244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5496244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101922900","display_name":"J\u00f6rg-Hendrik Bach","orcid":"https://orcid.org/0000-0001-5205-2193"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorg-Hendrik Bach","raw_affiliation_strings":["Dept. of Physics, Carl von Ossietzky University Oldenburg, Oldenburg, Germany","Medical Physics, Dept. of Physics, Carl von Ossietzky University Oldenburg, 26111, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Physics, Carl von Ossietzky University Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Medical Physics, Dept. of Physics, Carl von Ossietzky University Oldenburg, 26111, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076869895","display_name":"Birger Kollmeier","orcid":"https://orcid.org/0000-0001-8584-4779"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Birger Kollmeier","raw_affiliation_strings":["Dept. of Physics, Carl von Ossietzky University Oldenburg, Oldenburg, Germany","Medical Physics, Dept. of Physics, Carl von Ossietzky University Oldenburg, 26111, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Physics, Carl von Ossietzky University Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Medical Physics, Dept. of Physics, Carl von Ossietzky University Oldenburg, 26111, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009092572","display_name":"J\u00f6rn Anem\u00fcller","orcid":"https://orcid.org/0000-0001-5564-5795"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorn Anemuller","raw_affiliation_strings":["Dept. of Physics, Carl von Ossietzky University Oldenburg, Oldenburg, Germany","Medical Physics, Dept. of Physics, Carl von Ossietzky University Oldenburg, 26111, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Physics, Carl von Ossietzky University Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"Medical Physics, Dept. of Physics, Carl von Ossietzky University Oldenburg, 26111, Germany","institution_ids":["https://openalex.org/I129877168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129877168"],"apc_list":null,"apc_paid":null,"fwci":2.8811,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.91983942,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.8010729551315308},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.768110990524292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6768527030944824},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6474332213401794},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5353264212608337},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.5290944576263428},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5077224969863892},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4841350018978119},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.47932755947113037},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.455203115940094},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.4546050429344177},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.42898571491241455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3963693380355835},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36314961314201355},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3278719186782837},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21167659759521484},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1966170370578766},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1066007912158966},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0781501829624176}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8010729551315308},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.768110990524292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6768527030944824},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6474332213401794},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5353264212608337},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.5290944576263428},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5077224969863892},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4841350018978119},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47932755947113037},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.455203115940094},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.4546050429344177},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.42898571491241455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3963693380355835},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36314961314201355},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3278719186782837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21167659759521484},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1966170370578766},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1066007912158966},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0781501829624176},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5496244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5496244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W35290520","https://openalex.org/W1964538581","https://openalex.org/W1971332722","https://openalex.org/W1999686891","https://openalex.org/W2041638389","https://openalex.org/W2130426352","https://openalex.org/W2138456300","https://openalex.org/W2149759367","https://openalex.org/W2153635508","https://openalex.org/W3120421331","https://openalex.org/W4256399001"],"related_works":["https://openalex.org/W2953493266","https://openalex.org/W1517805583","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2248536413","https://openalex.org/W2383417046","https://openalex.org/W4386336391","https://openalex.org/W3217417050","https://openalex.org/W2187296505"],"abstract_inverted_index":{"Robust":[0],"detection":[1,119],"of":[2,76,84],"speech":[3,36],"embedded":[4,38],"in":[5,30,34,39,74,111],"real":[6],"acoustic":[7,40],"background":[8,66],"noise":[9],"is":[10,28,37],"considered":[11],"using":[12],"an":[13,81],"approach":[14],"based":[15],"on":[16],"subband":[17],"amplitude":[18],"modulation":[19],"spectral":[20],"(AMS)":[21],"features":[22,70],"and":[23,47,100],"trained":[24],"discriminative":[25],"classifiers.":[26],"Performance":[27],"evaluated":[29],"particular":[31],"for":[32,48,109],"situations":[33],"which":[35],"backgrounds":[41],"not":[42],"presented":[43],"during":[44],"classifier":[45],"training,":[46],"signal-to-noise":[49],"ratios":[50],"(SNR)":[51],"from":[52],"-10":[53],"dB":[54,87],"to":[55,64,80,89],"20":[56],"dB.":[57],"The":[58],"results":[59],"show":[60],"that":[61],"(1)":[62],"Generalization":[63],"novel":[65],"classes":[67],"with":[68,105],"AMS":[69,99,110],"yields":[71],"better":[72],"performance":[73],"84%":[75],"investigated":[77],"situations,":[78],"corresponding":[79],"SNR":[82,113],"benefit":[83],"about":[85],"10":[86],"compared":[88],"mel-frequency":[90],"cepstral":[91],"coefficient":[92],"(MFCC)":[93],"features.":[94],"(2)":[95],"On":[96],"known":[97],"backgrounds,":[98],"MFCCs":[101],"achieve":[102],"similar":[103],"performance,":[104],"a":[106],"small":[107],"advantage":[108],"negative":[112],"regimes.":[114],"(3)":[115],"Standard":[116],"voice":[117],"activity":[118],"(ITU":[120],"G729.B)":[121],"performs":[122],"significantly":[123],"worse":[124],"than":[125],"the":[126],"classification-based":[127],"approach.":[128]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}