{"id":"https://openalex.org/W1981529741","doi":"https://doi.org/10.1109/lsp.2013.2266860","title":"Whispered Speech Detection in Noise Using Auditory-Inspired Modulation Spectrum Features","display_name":"Whispered Speech Detection in Noise Using Auditory-Inspired Modulation Spectrum Features","publication_year":2013,"publication_date":"2013-06-07","ids":{"openalex":"https://openalex.org/W1981529741","doi":"https://doi.org/10.1109/lsp.2013.2266860","mag":"1981529741"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2013.2266860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2013.2266860","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5050313485","display_name":"Milton Sarria-Paja","orcid":"https://orcid.org/0000-0003-4288-1742"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]},{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"M. Sarria-Paja","raw_affiliation_strings":["Institut National de la Recherche Scientifique (INRS-EMT), University of Quebec, Montreal, QUE, Canada","Inst. Nat. de la Rech. Sci. (INRS-EMT), Univ. of Quebec, Montre\u0301al, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut National de la Recherche Scientifique (INRS-EMT), University of Quebec, Montreal, QUE, Canada","institution_ids":["https://openalex.org/I159129438","https://openalex.org/I39481719"]},{"raw_affiliation_string":"Inst. Nat. de la Rech. Sci. (INRS-EMT), Univ. of Quebec, Montre\u0301al, QC, Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065418889","display_name":"Tiago H. Falk","orcid":"https://orcid.org/0000-0002-5739-2514"},"institutions":[{"id":"https://openalex.org/I159129438","display_name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al","ror":"https://ror.org/002rjbv21","country_code":"CA","type":"education","lineage":["https://openalex.org/I159129438","https://openalex.org/I49663120"]},{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"T. H. Falk","raw_affiliation_strings":["Institut National de la Recherche Scientifique (INRS-EMT), University of Quebec, Montreal, QUE, Canada","Inst. Nat. de la Rech. Sci. (INRS-EMT), Univ. of Quebec, Montre\u0301al, QC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut National de la Recherche Scientifique (INRS-EMT), University of Quebec, Montreal, QUE, Canada","institution_ids":["https://openalex.org/I159129438","https://openalex.org/I39481719"]},{"raw_affiliation_string":"Inst. Nat. de la Rech. Sci. (INRS-EMT), Univ. of Quebec, Montre\u0301al, QC, Canada","institution_ids":["https://openalex.org/I39481719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2545,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.8784642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"8","first_page":"783","last_page":"786"},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/speech-recognition","display_name":"Speech recognition","score":0.7956365346908569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7841145992279053},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7388874888420105},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6905959844589233},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.643462061882019},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5764918923377991},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5266687273979187},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.49219241738319397},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4603751301765442},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4421547055244446},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4328259825706482},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.4267440438270569},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.42347386479377747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34681692719459534},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24331972002983093},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09943735599517822},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.09580343961715698}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7956365346908569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7841145992279053},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7388874888420105},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6905959844589233},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.643462061882019},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5764918923377991},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5266687273979187},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.49219241738319397},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4603751301765442},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4421547055244446},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4328259825706482},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.4267440438270569},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.42347386479377747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34681692719459534},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24331972002983093},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09943735599517822},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.09580343961715698},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/lsp.2013.2266860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2013.2266860","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W163913193","https://openalex.org/W1965504810","https://openalex.org/W2088522790","https://openalex.org/W2095161034","https://openalex.org/W2107570013","https://openalex.org/W2109225367","https://openalex.org/W2118479009","https://openalex.org/W2125514156","https://openalex.org/W2127707623","https://openalex.org/W2146618065","https://openalex.org/W2151046079","https://openalex.org/W2155517073","https://openalex.org/W2395582662","https://openalex.org/W6711912575"],"related_works":["https://openalex.org/W4214896311","https://openalex.org/W2294333436","https://openalex.org/W1990055248","https://openalex.org/W2653598178","https://openalex.org/W2907713742","https://openalex.org/W2135485548","https://openalex.org/W2165935979","https://openalex.org/W1975881626","https://openalex.org/W4252208810","https://openalex.org/W2373767407"],"abstract_inverted_index":{"Robustness":[0],"to":[1,38],"ambient":[2],"noise,":[3],"varying":[4],"vocal":[5,30],"effort,":[6],"and":[7],"availability":[8],"of":[9,19,29,59,67],"only":[10],"short-duration":[11],"test":[12],"utterances":[13],"represent":[14],"big":[15],"challenges":[16],"for":[17],"developers":[18],"automated":[20],"speech-enabled":[21],"applications.":[22],"Recent":[23],"studies":[24],"have":[25],"proposed":[26,92],"the":[27,57,91],"use":[28,58],"effort-matched":[31],"speaker":[32],"models":[33],"as":[34,64,83,85],"a":[35,51,65],"potential":[36],"solution":[37],"such":[39],"challenges.":[40],"However,":[41],"detecting":[42],"whispered":[43,77],"speech":[44,69,78],"in":[45,75],"extremely":[46],"noisy":[47],"environments":[48],"is":[49],"not":[50],"trivial":[52],"task.":[53],"This":[54],"letter":[55],"proposes":[56],"auditory-inspired":[60],"modulation":[61],"spectral-based":[62],"features":[63],"method":[66],"separating":[68],"from":[70],"environment-based":[71],"components,":[72],"thus":[73],"resulting":[74],"accurate":[76],"detection":[79,93],"at":[80],"signal-to-noise":[81],"ratios":[82],"low":[84],"0":[86],"dB.":[87],"Experimental":[88],"results":[89],"show":[90],"algorithm":[94],"outperforming":[95],"two":[96],"benchmark":[97],"approaches.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"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"}