{"id":"https://openalex.org/W337595008","doi":"https://doi.org/10.21437/icslp.1998-328","title":"Robust automatic speech recognition by the application of a temporal-correlation-based recurrent multilayer neural network to the mel-based cepstral coefficients","display_name":"Robust automatic speech recognition by the application of a temporal-correlation-based recurrent multilayer neural network to the mel-based cepstral coefficients","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W337595008","doi":"https://doi.org/10.21437/icslp.1998-328","mag":"337595008"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-328","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5010781605","display_name":"Michel H\u00e9on","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Michel H\u00e9on","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110302454","display_name":"Hesham Tolba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hesham Tolba","raw_affiliation_strings":[],"affiliations":[]},{"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/I49663120","display_name":"Universit\u00e9 du Qu\u00e9bec","ror":"https://ror.org/010gxg263","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Douglas O'Shaughnessy","raw_affiliation_strings":["Univ. of Qu\u00e9bec"],"affiliations":[{"raw_affiliation_string":"Univ. of Qu\u00e9bec","institution_ids":["https://openalex.org/I49663120"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010781605"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04034324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 0807","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9993000030517578,"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":0.7634857892990112},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7363135814666748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7344724535942078},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7262959480285645},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.656583845615387},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5904040336608887},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5521140694618225},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5336034893989563},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5305460095405579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5196838974952698},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.47361159324645996},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4581339657306671},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.41416236758232117},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4123893976211548},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1278526484966278}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7634857892990112},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7363135814666748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7344724535942078},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7262959480285645},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.656583845615387},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5904040336608887},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5521140694618225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5336034893989563},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5305460095405579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5196838974952698},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.47361159324645996},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4581339657306671},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.41416236758232117},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4123893976211548},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1278526484966278},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.1998-328","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W22549796","https://openalex.org/W1994396704","https://openalex.org/W2038054257","https://openalex.org/W2069976350","https://openalex.org/W2109293211","https://openalex.org/W2109816922","https://openalex.org/W2112529238","https://openalex.org/W2124776405","https://openalex.org/W2144521324","https://openalex.org/W2148154194","https://openalex.org/W2467500531"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W3134920593","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,17,21,30,45,68,71,79,83,106,117,120,130],"problem":[4],"of":[5,20,70,82,105,119,133,152],"robust":[6,60],"speech":[7,85,123],"recognition":[8,61,80,86,124,131],"has":[9],"been":[10,146],"considered.":[11],"Our":[12],"approach":[13,77],"is":[14,48],"based":[15],"on":[16,101],"noise":[18,42,113],"reduction":[19,43,114],"parameters":[22,55,73],"that":[23,28,67],"we":[24],"use":[25,69],"for":[26,41,59],"recognition,":[27],"is,":[29],"Mel-based":[31],"cepstral":[32,46],"coefficients.":[33],"A":[34],"Temporal-Correlation-Based":[35],"Recurrent":[36],"Multilayer":[37],"Neural":[38],"Network":[39],"(TCRMNN)":[40],"in":[44,50,62,116,129],"domain":[47],"used":[49,96],"order":[51],"to":[52,56],"get":[53],"less-variant":[54],"be":[57],"useful":[58],"noisy":[63,103],"environments.":[64],"Experiments":[65,98],"show":[66],"enhanced":[72],"using":[74,138],"such":[75,110],"an":[76],"increases":[78],"rate":[81],"continuous":[84,122],"(CSR)":[87,126],"process.":[88],"The":[89],"HTK":[90],"Hidden":[91],"Markov":[92],"Model":[93],"Toolkit":[94],"was":[95],"throughout.":[97],"were":[99],"done":[100],"a":[102,111,149],"version":[104],"TIMIT":[107],"database.":[108],"With":[109],"pre-processing":[112],"technique":[115],"front-end":[118],"HTK-based":[121],"system":[125],"system,":[127],"improvements":[128],"accuracy":[132],"about":[134],"17.77%":[135],"and":[136,142],"18.58%":[137],"single":[139],"mixture":[140],"monophones":[141],"triphones,":[143],"respectively,":[144],"have":[145],"obtained":[147],"at":[148],"moderate":[150],"SNR":[151],"20":[153],"dB.":[154]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}