{"id":"https://openalex.org/W2404926044","doi":"https://doi.org/10.21437/interspeech.2014-226","title":"Robust CNN-based speech recognition with Gabor filter kernels","display_name":"Robust CNN-based speech recognition with Gabor filter kernels","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2404926044","doi":"https://doi.org/10.21437/interspeech.2014-226","mag":"2404926044"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-226","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5001306222","display_name":"Shuo-Yiin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shuo-Yiin Chang","raw_affiliation_strings":["University of California\u2013Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112003894","display_name":"Nelson Morgan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nelson Morgan","raw_affiliation_strings":["University of California\u2013Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001306222"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":8.0183,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.97539602,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"905","last_page":"909"},"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":0.9995999932289124,"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":0.9991000294685364,"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":0.7122511267662048},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6155821681022644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5562310218811035},{"id":"https://openalex.org/keywords/gabor-filter","display_name":"Gabor filter","score":0.5222350358963013},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5145013332366943},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.45045027136802673},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3723199963569641},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2865259051322937},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2749015688896179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7122511267662048},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6155821681022644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562310218811035},{"id":"https://openalex.org/C2779883129","wikidata":"https://www.wikidata.org/wiki/Q2447890","display_name":"Gabor filter","level":3,"score":0.5222350358963013},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5145013332366943},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.45045027136802673},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3723199963569641},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2865259051322937},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2749015688896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-226","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W197151588","https://openalex.org/W1492775261","https://openalex.org/W1553004968","https://openalex.org/W1627087495","https://openalex.org/W1993882792","https://openalex.org/W2035305631","https://openalex.org/W2062164080","https://openalex.org/W2072349636","https://openalex.org/W2088489891","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2118640610","https://openalex.org/W2123840324","https://openalex.org/W2140595311","https://openalex.org/W2140979961","https://openalex.org/W2160815625","https://openalex.org/W2161025448","https://openalex.org/W2165712214","https://openalex.org/W2167763959","https://openalex.org/W2188183693","https://openalex.org/W2407881408","https://openalex.org/W2887979278"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2356578509","https://openalex.org/W2607673196","https://openalex.org/W2366228691","https://openalex.org/W2350842752","https://openalex.org/W2126328176","https://openalex.org/W2353445273","https://openalex.org/W1999926881","https://openalex.org/W2110603634","https://openalex.org/W21556450"],"abstract_inverted_index":{"As":[0],"has":[1],"been":[2],"extensively":[3],"shown,":[4],"acoustic":[5],"features":[6,61,110,156,165,175],"for":[7,73],"speech":[8,74],"recognition":[9,75],"can":[10],"be":[11],"learned":[12,22],"from":[13,48],"neural":[14,67,85,173],"networks":[15],"with":[16],"multiple":[17,114],"hidden":[18],"layers.":[19],"However,":[20],"the":[21,37,43,77,113,118,136,148,167],"transformations":[23],"may":[24],"not":[25],"sufficiently":[26],"generalize":[27],"to":[28,36,52,66],"test":[29],"sets":[30],"that":[31,95,157,176],"have":[32,159],"a":[33,84,89,106],"significant":[34],"mismatch":[35],"training":[38],"data.":[39],"Gabor":[40,90,97,109,164,179],"features,":[41],"on":[42],"other":[44,154],"hand,":[45],"are":[46,62,124],"generated":[47],"spectro-temporal":[49],"filters":[50],"designed":[51],"model":[53],"human":[54],"auditory":[55],"processing.":[56],"In":[57,103,145],"previous":[58],"work,":[59],"these":[60],"used":[63,131],"as":[64,112],"inputs":[65],"networks,":[68],"which":[69],"improved":[70],"word":[71],"accuracy":[72],"in":[76],"presence":[78],"of":[79,108,117,135],"noise.":[80],"Here":[81],"we":[82,158],"propose":[83],"network":[86,174],"architecture":[87,150],"called":[88],"Convolutional":[91],"Neural":[92],"Network":[93],"(GCNN)":[94],"incorporates":[96],"functions":[98],"into":[99],"convolutional":[100,119],"filter":[101,122],"kernels.":[102],"this":[104],"architecture,":[105],"variety":[107],"served":[111],"feature":[115],"maps":[116],"layer.":[120],"The":[121],"coefficients":[123],"further":[125],"tuned":[126],"by":[127],"back-propagation":[128],"training.":[129],"Experiments":[130],"two":[132],"noisy":[133],"versions":[134],"WSJ":[137],"corpus:":[138],"Aurora":[139],"4,":[140],"and":[141,170],"RATS":[142],"re-noised":[143],"WSJ.":[144],"both":[146],"cases,":[147],"proposed":[149],"performs":[151],"better":[152],"than":[153],"noise-robust":[155],"tried,":[160],"namely,":[161],"ETSI-AFE,":[162],"PNCC,":[163],"without":[166],"CNN-based":[168],"approach,":[169],"our":[171],"best":[172],"don\u2019t":[177],"incorporate":[178],"functions.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9}],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}