{"id":"https://openalex.org/W2808687072","doi":"https://doi.org/10.1109/icsda.2017.8384470","title":"Multiresolution CNN for reverberant speech recognition","display_name":"Multiresolution CNN for reverberant speech recognition","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2808687072","doi":"https://doi.org/10.1109/icsda.2017.8384470","mag":"2808687072"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2017.8384470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","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/A5077698897","display_name":"Sunchan Park","orcid":"https://orcid.org/0009-0004-2145-819X"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sunchan Park","raw_affiliation_strings":["Department of Electronics Engineering, Pusan National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Pusan National University, Republic of Korea","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111642033","display_name":"Yongwon Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongwon Jeong","raw_affiliation_strings":["Department of Electronics Engineering, Pusan National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Pusan National University, Republic of Korea","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073733529","display_name":"Hyung Soon Kim","orcid":"https://orcid.org/0000-0001-5070-897X"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung Soon Kim","raw_affiliation_strings":["Department of Electronics Engineering, Pusan National University, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electronics Engineering, Pusan National University, Republic of Korea","institution_ids":["https://openalex.org/I4921948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077698897"],"corresponding_institution_ids":["https://openalex.org/I4921948"],"apc_list":null,"apc_paid":null,"fwci":1.4794,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.84509763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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":0.8256016969680786},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7572470903396606},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6905248165130615},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5709580183029175},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5650306344032288},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5489268898963928},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5248420238494873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5155251026153564},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4492276906967163},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42585495114326477},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2852140963077545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256016969680786},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7572470903396606},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6905248165130615},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5709580183029175},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5650306344032288},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5489268898963928},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5248420238494873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5155251026153564},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4492276906967163},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42585495114326477},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2852140963077545},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsda.2017.8384470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384470","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W2016053056","https://openalex.org/W2033310064","https://openalex.org/W2103088716","https://openalex.org/W2112739286","https://openalex.org/W2130722890","https://openalex.org/W2147166770","https://openalex.org/W2181607856","https://openalex.org/W2242685705","https://openalex.org/W2515753980","https://openalex.org/W6631362777","https://openalex.org/W6679230416","https://openalex.org/W6686045668"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W113247760","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"The":[0,88],"performance":[1,51],"of":[2,52,94],"automatic":[3],"speech":[4,41,54],"recognition":[5,42,55],"(ASR)":[6],"has":[7,66],"been":[8],"greatly":[9],"improved":[10],"by":[11,110],"deep":[12],"neural":[13,28],"network":[14,29],"(DNN)":[15],"acoustic":[16,31,46,58],"models.":[17,47],"However,":[18],"DNN-based":[19],"systems":[20],"still":[21],"perform":[22],"poorly":[23],"in":[24,39],"reverberant":[25,53],"environments.":[26],"Convolutional":[27],"(CNN)":[30],"models":[32],"showed":[33,99],"lower":[34],"word":[35],"error":[36],"rate":[37],"(WER)":[38],"distant":[40],"than":[43],"fully-connected":[44],"DNN":[45],"To":[48],"improve":[49],"the":[50,62,72,79,82,91,95,101,108,115,120,127],"using":[56],"CNN":[57,64,104,129],"models,":[59],"we":[60],"propose":[61],"multiresolution":[63,103],"that":[65,100],"two":[67],"separate":[68],"streams:":[69],"one":[70],"is":[71,81],"wideband":[73],"feature":[74,84],"with":[75,85,126],"wide-context":[76],"window":[77],"and":[78,112,119],"other":[80],"narrowband":[83],"narrow-context":[86],"window.":[87],"experiments":[89],"on":[90],"ASR":[92],"task":[93],"REVERB":[96],"challenge":[97],"2014":[98],"proposed":[102],"based":[105,130],"approach":[106],"reduced":[107],"WER":[109],"8.79%":[111],"8.83%":[113],"for":[114],"simulated":[116],"test":[117,122],"data":[118],"real-condition":[121],"data,":[123],"respectively,":[124],"compared":[125],"conventional":[128],"method.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}