{"id":"https://openalex.org/W2400523955","doi":"https://doi.org/10.21437/interspeech.2011-103","title":"Comparing different flavors of spectro-temporal features for ASR","display_name":"Comparing different flavors of spectro-temporal features for ASR","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2400523955","doi":"https://doi.org/10.21437/interspeech.2011-103","mag":"2400523955"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-103","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5067491941","display_name":"Bernd T. Meyer","orcid":"https://orcid.org/0000-0001-9190-2111"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bernd T. Meyer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026262869","display_name":"Suman Ravuri","orcid":"https://orcid.org/0000-0002-7481-7633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suman V. Ravuri","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079185756","display_name":"Marc Ren\u00e9 Sch\u00e4dler","orcid":"https://orcid.org/0000-0001-6731-7377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Ren\u00e9 Sch\u00e4dler","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112003894","display_name":"Nelson Morgan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nelson Morgan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067491941"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8183,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.97005789,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1269","last_page":"1272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9990000128746033,"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/T12131","display_name":"Wireless Signal Modulation Classification","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7309859991073608},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7051211595535278},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7036224603652954},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.645512580871582},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6100601553916931},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5950725674629211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5502932667732239},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5480456948280334},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5296280980110168},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.4737461507320404},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41403186321258545},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3517799973487854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.20831656455993652},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1993836760520935},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1673131287097931},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09857594966888428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7309859991073608},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7051211595535278},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7036224603652954},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.645512580871582},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6100601553916931},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5950725674629211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5502932667732239},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5480456948280334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5296280980110168},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.4737461507320404},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41403186321258545},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3517799973487854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.20831656455993652},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1993836760520935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1673131287097931},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09857594966888428},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-103","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5899999737739563,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W9692546","https://openalex.org/W34609997","https://openalex.org/W96378396","https://openalex.org/W1990934990","https://openalex.org/W2027890689","https://openalex.org/W2064280544","https://openalex.org/W2148154194","https://openalex.org/W2151484683","https://openalex.org/W2158010000","https://openalex.org/W2163680580","https://openalex.org/W2166067691"],"related_works":["https://openalex.org/W2888091758","https://openalex.org/W2766680336","https://openalex.org/W2134209752","https://openalex.org/W2133320490","https://openalex.org/W4289830142","https://openalex.org/W1497065097","https://openalex.org/W2125446021","https://openalex.org/W3150393935","https://openalex.org/W2980055100","https://openalex.org/W2186790562"],"abstract_inverted_index":{"In":[0],"the":[1,9,29,81,87,94,117,120],"last":[2],"decade,":[3],"several":[4],"studies":[5],"have":[6,112],"shown":[7],"that":[8,52,100],"robustness":[10],"of":[11,89,137],"ASR":[12],"systems":[13],"can":[14],"be":[15],"increased":[16],"when":[17],"2D":[18],"Gabor":[19,44],"filters":[20,51,92,99,129],"are":[21],"used":[22],"to":[23],"extract":[24],"specific":[25],"modulation":[26],"frequencies":[27],"from":[28],"input":[30],"pattern.":[31],"This":[32],"paper":[33],"analyzes":[34],"important":[35],"design":[36],"parameters":[37],"for":[38,125,140],"spectro-temporal":[39],"features":[40],"based":[41],"on":[42,116],"a":[43,64,69,113],"filter":[45],"bank:":[46],"We":[47],"perform":[48],"experiments":[49],"with":[50,63,72,133],"exhibit":[53],"different":[54],"phase":[55,90,102,127],"sensitivity.":[56],"Further,":[57],"we":[58],"analyze":[59],"if":[60],"non-linear":[61],"weighting":[62],"multi-layer":[65],"perceptron":[66],"(MLP)":[67],"and":[68,130,143],"subsequent":[70],"concatenation":[71],"mel-frequency":[73],"cepstral":[74],"coefficients":[75],"(MFCCs)":[76],"has":[77],"beneficial":[78],"effects.":[79],"For":[80],"Aurora2":[82],"noisy":[83,142],"digit":[84],"recognition":[85],"task,":[86],"use":[88],"sensitive":[91,128],"improved":[93],"MFCC":[95],"baseline,":[96],"whereas":[97],"using":[98],"neglect":[101],"information":[103],"did":[104,110],"not.":[105],"While":[106],"MLP":[107],"processing":[108],"alone":[109],"not":[111],"large":[114],"effect":[115],"overall":[118],"performance,":[119],"best":[121],"results":[122],"were":[123],"obtained":[124],"MLP-processed":[126],"added":[131],"MFCCs,":[132],"relative":[134],"error":[135],"reductions":[136],"over":[138],"40%":[139],"both":[141],"clean":[144],"training.":[145]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}