{"id":"https://openalex.org/W2404548287","doi":"https://doi.org/10.21437/interspeech.2012-386","title":"Hooking up spectro-temporal filters with auditory-inspired representations for robust automatic speech recognition","display_name":"Hooking up spectro-temporal filters with auditory-inspired representations for robust automatic speech recognition","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2404548287","doi":"https://doi.org/10.21437/interspeech.2012-386","mag":"2404548287"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-386","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Bernd T. Meyer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036912609","display_name":"Constantin Spille","orcid":"https://orcid.org/0000-0002-4226-7470"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Constantin Spille","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076869895","display_name":"Birger Kollmeier","orcid":"https://orcid.org/0000-0001-8584-4779"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Birger Kollmeier","raw_affiliation_strings":[],"raw_orcid":null,"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":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1259","last_page":"1262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9980999827384949,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9113352298736572},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6961507797241211},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.690668523311615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6835160255432129},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.598916232585907},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5340715050697327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5340710282325745},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5214471220970154},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.48945558071136475},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46164339780807495},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.432420551776886},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.42638224363327026},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.4233786463737488},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41845065355300903},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.382446825504303},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.22856569290161133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22840315103530884},{"id":"https://openalex.org/keywords/radio-frequency","display_name":"Radio frequency","score":0.15286186337471008},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.11093801259994507}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9113352298736572},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6961507797241211},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.690668523311615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6835160255432129},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.598916232585907},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5340715050697327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5340710282325745},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5214471220970154},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.48945558071136475},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46164339780807495},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.432420551776886},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.42638224363327026},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.4233786463737488},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41845065355300903},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.382446825504303},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.22856569290161133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22840315103530884},{"id":"https://openalex.org/C74064498","wikidata":"https://www.wikidata.org/wiki/Q3396184","display_name":"Radio frequency","level":2,"score":0.15286186337471008},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.11093801259994507},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2012-386","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W9692546","https://openalex.org/W34609997","https://openalex.org/W1489184006","https://openalex.org/W1607274768","https://openalex.org/W1990934990","https://openalex.org/W2106405099","https://openalex.org/W2151484683","https://openalex.org/W2158010000","https://openalex.org/W2400523955"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2288135719","https://openalex.org/W2327143552","https://openalex.org/W1889291648","https://openalex.org/W2533590149","https://openalex.org/W2381036744","https://openalex.org/W2901989338","https://openalex.org/W2323749021","https://openalex.org/W2909460703"],"abstract_inverted_index":{"Spectro-temporal":[0],"filtering":[1],"has":[2],"been":[3],"shown":[4],"to":[5,12,60,63,78,133],"result":[6],"in":[7,21,30],"features":[8,65,127],"that":[9,35],"can":[10],"help":[11],"increase":[13],"the":[14,22,26,39,43,79,84,99,129,134],"robustness":[15],"of":[16,42,95,102,113],"automatic":[17],"speech":[18],"recognition":[19,71],"(ASR)":[20],"past.":[23],"We":[24],"replace":[25],"spectro-temporal":[27],"representation":[28,81],"used":[29],"previous":[31],"work":[32],"with":[33,89,117,124],"spectrograms":[34,62],"incorporate":[36],"knowledge":[37],"about":[38],"signal":[40],"processing":[41],"human":[44],"auditory":[45],"system":[46],"and":[47,98,110,122,136],"which":[48],"are":[49,58],"derived":[50],"from":[51],"Power-Normalized":[52],"Cepstral":[53],"Coefficients":[54],"(PNCCs).":[55],"2D-Gabor":[56],"filters":[57],"applied":[59],"these":[61],"extract":[64],"evaluated":[66],"on":[67],"a":[68,105,118],"noisy":[69],"digit":[70],"task.":[72],"The":[73],"filter":[74],"bank":[75],"is":[76],"adapted":[77],"new":[80],"by":[82,138],"optimizing":[83],"spectral":[85,100],"modulation":[86,101],"frequencies":[87],"associated":[88],"each":[90],"Gabor":[91,126],"function.":[92],"A":[93],"comparison":[94],"optimized":[96,109],"parameters":[97],"vowels":[103],"shows":[104],"good":[106],"match":[107],"between":[108],"expected":[111],"range":[112],"frequencies.":[114],"When":[115],"processed":[116],"non-linear":[119],"neural":[120],"net":[121],"combined":[123],"PNCCs,":[125],"decrease":[128],"error":[130],"rate":[131],"compared":[132],"baseline":[135],"PNCCs":[137],"at":[139],"least":[140],"19%.":[141]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}