{"id":"https://openalex.org/W2153677414","doi":"https://doi.org/10.1109/iros.2011.6094672","title":"Variable frame rate hierarchical analysis for robust speech recognition","display_name":"Variable frame rate hierarchical analysis for robust speech recognition","publication_year":2011,"publication_date":"2011-09-01","ids":{"openalex":"https://openalex.org/W2153677414","doi":"https://doi.org/10.1109/iros.2011.6094672","mag":"2153677414"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2011.6094672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2011.6094672","pdf_url":null,"source":{"id":"https://openalex.org/S4363608614","display_name":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","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":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","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/A5026332327","display_name":"Jean Rouat","orcid":"https://orcid.org/0000-0002-9306-426X"},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jean Rouat","raw_affiliation_strings":["NECOTIS, GEGI, University de Sherbrooke, QUE, Canada"],"affiliations":[{"raw_affiliation_string":"NECOTIS, GEGI, University de Sherbrooke, QUE, Canada","institution_ids":["https://openalex.org/I135117807"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072037625","display_name":"St\u00e9phane Loiselle","orcid":null},"institutions":[{"id":"https://openalex.org/I135117807","display_name":"Universit\u00e9 de Sherbrooke","ror":"https://ror.org/00kybxq39","country_code":"CA","type":"education","lineage":["https://openalex.org/I135117807"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Stephane Loiselle","raw_affiliation_strings":["NECOTIS, GEGI, University de Sherbrooke, QUE, Canada"],"affiliations":[{"raw_affiliation_string":"NECOTIS, GEGI, University de Sherbrooke, QUE, Canada","institution_ids":["https://openalex.org/I135117807"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022413086","display_name":"St\u00e9phane Molotchnikoff","orcid":"https://orcid.org/0000-0002-3063-2063"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephane Molotchnikoff","raw_affiliation_strings":["NECOTIS, GEGI, University de Montr\u00e9al, QUE, Canada"],"affiliations":[{"raw_affiliation_string":"NECOTIS, GEGI, University de Montr\u00e9al, QUE, Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026332327"],"corresponding_institution_ids":["https://openalex.org/I135117807"],"apc_list":null,"apc_paid":null,"fwci":0.5498,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67664671,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"518","last_page":"523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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/T11447","display_name":"Blind Source Separation Techniques","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/speech-recognition","display_name":"Speech recognition","score":0.8435150384902954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8204034566879272},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.765211820602417},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.645331621170044},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5456169843673706},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5450610518455505},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49705222249031067},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4711258113384247},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4696967601776123},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4581533670425415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4413682520389557},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40917491912841797},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3757559061050415},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08470794558525085}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8435150384902954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8204034566879272},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.765211820602417},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.645331621170044},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5456169843673706},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5450610518455505},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49705222249031067},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4711258113384247},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4696967601776123},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4581533670425415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4413682520389557},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40917491912841797},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3757559061050415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08470794558525085},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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":2,"locations":[{"id":"doi:10.1109/iros.2011.6094672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2011.6094672","pdf_url":null,"source":{"id":"https://openalex.org/S4363608614","display_name":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","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":"2011 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.719.208","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.719.208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gel.usherbrooke.ca/rouat/publications/IROSRouatLoiselleMolotchnikoff2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W101771737","https://openalex.org/W181136134","https://openalex.org/W182831726","https://openalex.org/W289804034","https://openalex.org/W1517009156","https://openalex.org/W1536018596","https://openalex.org/W1575566382","https://openalex.org/W1578457181","https://openalex.org/W1890977971","https://openalex.org/W1964705026","https://openalex.org/W1965248225","https://openalex.org/W1995453281","https://openalex.org/W1996255164","https://openalex.org/W2006370340","https://openalex.org/W2013020033","https://openalex.org/W2029053547","https://openalex.org/W2029683515","https://openalex.org/W2049633694","https://openalex.org/W2059450962","https://openalex.org/W2060561757","https://openalex.org/W2065625684","https://openalex.org/W2067010796","https://openalex.org/W2074354966","https://openalex.org/W2081753968","https://openalex.org/W2114827915","https://openalex.org/W2115008841","https://openalex.org/W2117678320","https://openalex.org/W2117731089","https://openalex.org/W2123317875","https://openalex.org/W2123544472","https://openalex.org/W2136571737","https://openalex.org/W2151484683","https://openalex.org/W2167610553","https://openalex.org/W2329822579","https://openalex.org/W2436461459","https://openalex.org/W4254930485","https://openalex.org/W6630928080","https://openalex.org/W6677499506","https://openalex.org/W6701938693","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W2074132948","https://openalex.org/W2160511961"],"abstract_inverted_index":{"A":[0],"new":[1],"bio-inspired":[2,79],"speech":[3,9,24,28,80,117,164,180],"analysis":[4,47,129],"system":[5,67,205],"that":[6],"extracts":[7],"acoustical":[8,114],"events":[10,123],"is":[11,88],"proposed":[12,45,66],"and":[13,34,48,90,107,145,153,165,227],"used":[14,42,104],"in":[15,64,211],"the":[16,44,61,65,69,100,109,113,136,143,183,193],"design":[17],"of":[18,76,116,142],"a":[19,77,200,215],"variable":[20],"frame":[21,51],"rate":[22,52],"(VFR)":[23],"recognizer.":[25],"The":[26],"same":[27],"recognizer":[29],"(Hidden":[30],"Markov":[31],"Model":[32],"-HMM-":[33],"Mel":[35],"Frequency":[36],"Cepstrum":[37],"Coefficients":[38],"-MFCC-)":[39],"has":[40,159],"been":[41,160],"with":[43,57,188,199],"VFR":[46,59,204],"conventional":[49],"fixed":[50],"(FFR)":[53],"approach.":[54],"In":[55,197],"comparison":[56,198],"other":[58],"recognizers,":[60],"hierarchical":[62,148],"features":[63,150],"have":[68],"potential":[70],"to":[71,96,105,134,171,174],"serve":[72],"as":[73],"classification":[74],"parameters":[75],"complete":[78],"recognition":[81,166,212,220],"system.":[82,101],"Also,":[83],"no":[84,93],"voice":[85],"activity":[86],"detection":[87],"required":[89],"there":[91],"are":[92,103,118,124,156,224],"hard":[94],"decisions":[95],"be":[97,132],"taken":[98,191],"by":[99,139,181],"Events":[102],"label":[106],"identify":[108],"moments":[110],"at":[111],"which":[112,127],"properties":[115],"stable":[119],"or":[120,178],"changing.":[121],"These":[122],"markers":[125],"on":[126,162,167],"an":[128],"window":[130],"can":[131],"positioned":[133],"perform":[135],"recognition.":[137],"Inspired":[138],"our":[140,203],"knowledge":[141],"auditory":[144],"visual":[146],"systems,":[147],"complex":[149],"like":[151],"transients":[152],"energy":[154],"orientation":[155],"used.":[157],"Training":[158],"done":[161],"clean":[163],"noisy":[168],"(from":[169],"20dB":[170],"\u221210dB":[172],"Signal":[173],"Noise":[175],"Ratios":[176],"-SNR)":[177],"reverberated":[179],"using":[182],"TI":[184],"46-word":[185],"database":[186],"corrupted":[187],"4":[189],"noises":[190],"from":[192],"Aurora":[194],"2":[195],"data.":[196],"FFR":[201],"recognizer,":[202],"yields":[206],"more":[207],"than":[208],"50%":[209],"increase":[210],"rates":[213],"for":[214],"speaker":[216],"independent":[217],"isolated":[218],"word":[219],"task":[221],"when":[222],"SNRs":[223],"between":[225],"0":[226],"20":[228],"dB.":[229]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}