{"id":"https://openalex.org/W2135474356","doi":"https://doi.org/10.1109/icassp.2002.5743869","title":"Auditory-based acoustic distinctive features and spectral cues for automatic speech recognition using a multi-stream paradigm","display_name":"Auditory-based acoustic distinctive features and spectral cues for automatic speech recognition using a multi-stream paradigm","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2135474356","doi":"https://doi.org/10.1109/icassp.2002.5743869","mag":"2135474356"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743869","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5110302454","display_name":"Hesham Tolba","orcid":null},"institutions":[{"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":true,"raw_author_name":"Hesham Tolba","raw_affiliation_strings":["INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e0bec, Quebec, Canada","INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e9bec, 900 de la Gaucheti\u00e8re Ouest, H5A 1C6, Canada"],"affiliations":[{"raw_affiliation_string":"INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e0bec, Quebec, Canada","institution_ids":["https://openalex.org/I39481719"]},{"raw_affiliation_string":"INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e9bec, 900 de la Gaucheti\u00e8re Ouest, H5A 1C6, Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055849526","display_name":"Sid\u2010Ahmed Selouani","orcid":"https://orcid.org/0000-0003-0731-2632"},"institutions":[{"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":"Sid-Ahmed Selouani","raw_affiliation_strings":["INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e0bec, Quebec, Canada","INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e9bec, 900 de la Gaucheti\u00e8re Ouest, H5A 1C6, Canada"],"affiliations":[{"raw_affiliation_string":"INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e0bec, Quebec, Canada","institution_ids":["https://openalex.org/I39481719"]},{"raw_affiliation_string":"INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e9bec, 900 de la Gaucheti\u00e8re Ouest, H5A 1C6, Canada","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011489869","display_name":"Douglas O\u2019Shaughnessy","orcid":"https://orcid.org/0000-0002-0110-2346"},"institutions":[{"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":"Douglas O'Shaughnessy","raw_affiliation_strings":["INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e0bec, Quebec, Canada","INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e9bec, 900 de la Gaucheti\u00e8re Ouest, H5A 1C6, Canada"],"affiliations":[{"raw_affiliation_string":"INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e0bec, Quebec, Canada","institution_ids":["https://openalex.org/I39481719"]},{"raw_affiliation_string":"INRS-T\u00e9l\u00e9communications, Universit\u00e9 du Qu\u00e9bec, 900 de la Gaucheti\u00e8re Ouest, H5A 1C6, Canada","institution_ids":["https://openalex.org/I39481719"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110302454"],"corresponding_institution_ids":["https://openalex.org/I39481719"],"apc_list":null,"apc_paid":null,"fwci":0.3551,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.56426735,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"837"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8264068961143494},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8203228712081909},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.8114572763442993},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7898714542388916},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.664007306098938},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6282697916030884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4519228935241699},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44040441513061523},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38375362753868103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264068961143494},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8203228712081909},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.8114572763442993},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7898714542388916},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.664007306098938},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6282697916030884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4519228935241699},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44040441513061523},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38375362753868103},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743869","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1966127565","https://openalex.org/W1967199181","https://openalex.org/W2010800472","https://openalex.org/W2090861223","https://openalex.org/W2121551440","https://openalex.org/W2125610452","https://openalex.org/W2137075158","https://openalex.org/W7014675899"],"related_works":["https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W1990589093","https://openalex.org/W2067499868","https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2501000458","https://openalex.org/W2150890698","https://openalex.org/W1578749070","https://openalex.org/W1006721676"],"abstract_inverted_index":{"In":[0],"this":[1,21],"paper,":[2],"a":[3,76,80,125,141],"multi-stream":[4,81,109,135],"paradigm":[5,82],"is":[6,23],"proposed":[7],"to":[8,24,84,102],"improve":[9,25],"the":[10,26,29,43,50,59,69,73,88,104,107,128,148],"performance":[11,27],"of":[12,28,72,75,106,114,127],"automatic":[13],"speech":[14,39,77],"recognition":[15,89,119],"(ASR)":[16],"systems.":[17],"Our":[18],"goal":[19],"in":[20,87],"paper":[22],"HMM-based":[30],"ASR":[31],"systems":[32],"by":[33,154],"exploiting":[34],"some":[35,63],"features":[36],"that":[37,57,147],"characterize":[38],"sounds":[40],"based":[41,48],"on":[42,49,116],"auditory":[44],"system":[45],"and":[46,68,140],"one":[47],"Fourier":[51],"power":[52],"spectrum.":[53],"It":[54],"was":[55,97,152],"found":[56,146],"combining":[58],"classical":[60],"MFCCs":[61],"with":[62],"auditory-based":[64],"acoustic":[65],"distinctive":[66],"cues":[67],"main":[70],"peaks":[71],"spectrum":[74],"signal":[78],"using":[79,124],"leads":[83],"an":[85],"improvement":[86],"performance.":[90],"The":[91],"Hidden":[92],"Markov":[93],"Model":[94],"Toolkit":[95],"(HTK)":[96],"used":[98],"throughout":[99],"our":[100],"experiments":[101,115],"test":[103],"use":[105],"new":[108],"feature":[110],"vector.":[111],"A":[112],"series":[113],"speaker-independent":[117],"continuous-speech":[118],"have":[120],"been":[121],"carried":[122],"out":[123],"subset":[126],"large":[129],"read-speech":[130],"corpus":[131],"TIMIT.":[132],"Using":[133],"such":[134],"paradigm,":[136],"N-mixture":[137],"mono-/tri-phone":[138],"models":[139],"bigram":[142],"language":[143],"model,":[144],"we":[145],"word":[149],"error":[150],"rate":[151],"decreased":[153],"about":[155],"4.01%.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}