{"id":"https://openalex.org/W2169559282","doi":"https://doi.org/10.1109/icassp.2004.1325955","title":"Spectral entropy based feature for robust ASR","display_name":"Spectral entropy based feature for robust ASR","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2169559282","doi":"https://doi.org/10.1109/icassp.2004.1325955","mag":"2169559282"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1325955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/83008","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017720802","display_name":"Hemant Misra","orcid":"https://orcid.org/0000-0002-8179-4441"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"H. Misra","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053319645","display_name":"Shajith Ikbal","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"S. Ikbal","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108291827","display_name":"H. Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"H. Bourlard","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042260050","display_name":"Hynek He\u0159mansk\u00fd","orcid":"https://orcid.org/0000-0001-8032-4811"},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"H. Hermansky","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5513,"has_fulltext":false,"cited_by_count":181,"citation_normalized_percentile":{"value":0.95796972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"193"},"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":0.9997000098228455,"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":0.9984999895095825,"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/entropy","display_name":"Entropy (arrow of time)","score":0.6668152809143066},{"id":"https://openalex.org/keywords/maximum-entropy-spectral-estimation","display_name":"Maximum entropy spectral estimation","score":0.6528196334838867},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5865330100059509},{"id":"https://openalex.org/keywords/differential-entropy","display_name":"Differential entropy","score":0.5534800887107849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5222326517105103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5059356093406677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48398447036743164},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.47983571887016296},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4713945686817169},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4515973925590515},{"id":"https://openalex.org/keywords/joint-entropy","display_name":"Joint entropy","score":0.36239874362945557},{"id":"https://openalex.org/keywords/statistical-physics","display_name":"Statistical physics","score":0.32858580350875854},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14775139093399048},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.11803480982780457}],"concepts":[{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.6668152809143066},{"id":"https://openalex.org/C89735579","wikidata":"https://www.wikidata.org/wiki/Q6795894","display_name":"Maximum entropy spectral estimation","level":3,"score":0.6528196334838867},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5865330100059509},{"id":"https://openalex.org/C124551494","wikidata":"https://www.wikidata.org/wiki/Q3055345","display_name":"Differential entropy","level":4,"score":0.5534800887107849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5222326517105103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5059356093406677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48398447036743164},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.47983571887016296},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4713945686817169},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4515973925590515},{"id":"https://openalex.org/C106752470","wikidata":"https://www.wikidata.org/wiki/Q1364826","display_name":"Joint entropy","level":3,"score":0.36239874362945557},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.32858580350875854},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14775139093399048},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.11803480982780457},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2004.1325955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.474.2323","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.474.2323","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/reports/2003/rr03-56.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:83008","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83008","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:83132","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83132","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:83008","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228427","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"report"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:83008","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83008","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W204308143","https://openalex.org/W1493299544","https://openalex.org/W1560013842","https://openalex.org/W1974387177","https://openalex.org/W2041905826","https://openalex.org/W2090861223","https://openalex.org/W2103621378","https://openalex.org/W2137075158","https://openalex.org/W2168758670","https://openalex.org/W2993383518","https://openalex.org/W6608245754","https://openalex.org/W6685003409"],"related_works":["https://openalex.org/W2058254584","https://openalex.org/W2889261288","https://openalex.org/W1966654446","https://openalex.org/W59993211","https://openalex.org/W2161544911","https://openalex.org/W2034921015","https://openalex.org/W1519338247","https://openalex.org/W4246675730","https://openalex.org/W1990645539","https://openalex.org/W3206579266"],"abstract_inverted_index":{"In":[0],"general,":[1],"entropy":[2,25,41,109,122,131],"gives":[3],"us":[4],"a":[5,35,43,66,85,107],"measure":[6,31],"of":[7,10,34,42,70,77,106,143],"the":[8,20,32,40,75,104,114,141],"number":[9],"bits":[11],"required":[12],"to":[13,19,30,89],"represent":[14],"some":[15],"information.":[16],"When":[17],"applied":[18],"probability":[21],"mass":[22],"function":[23],"(PMF),":[24],"can":[26],"also":[27],"be":[28],"used":[29,133],"\"peakiness\"":[33],"distribution.":[36],"We":[37],"propose":[38],"using":[39],"short":[44],"time":[45],"Fourier":[46],"transform":[47],"spectrum,":[48,68,87],"normalised":[49],"as":[50,52],"PMF,":[51],"an":[53,144],"additional":[54],"feature":[55,110],"for":[56],"automatic":[57],"speech":[58],"recognition":[59],"(ASR).":[60],"It":[61],"is":[62],"indeed":[63],"expected":[64],"that":[65,129],"peaky":[67],"representation":[69],"clear":[71],"formant":[72],"structure":[73],"in":[74,123,134],"case":[76],"voiced":[78],"sounds,":[79],"will":[80,94],"have":[81,95],"low":[82],"entropy,":[83],"while":[84],"flatter":[86],"corresponding":[88],"nonspeech":[90],"or":[91],"noisy":[92],"regions,":[93],"higher":[96],"entropy.":[97],"Extending":[98],"this":[99],"reasoning":[100],"further,":[101],"we":[102,112],"introduce":[103],"idea":[105],"multiband/multiresolution":[108],"where":[111],"divide":[113],"spectrum":[115],"into":[116],"equal":[117],"size":[118],"subbands":[119],"and":[120],"compute":[121],"each":[124],"subband.":[125],"The":[126],"results":[127],"show":[128],"multiband":[130],"features":[132,139],"conjunction":[135],"with":[136],"normal":[137],"cepstral":[138],"improve":[140],"performance":[142],"ASR":[145],"system.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
