{"id":"https://openalex.org/W2938395714","doi":"https://doi.org/10.1109/icassp.2019.8683047","title":"Spatial and Channel Attention Based Convolutional Neural Networks for Modeling Noisy Speech","display_name":"Spatial and Channel Attention Based Convolutional Neural Networks for Modeling Noisy Speech","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938395714","doi":"https://doi.org/10.1109/icassp.2019.8683047","mag":"2938395714"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5111241700","display_name":"Sirui Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sirui Xu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6625","last_page":"6629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.8046197891235352},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7363752126693726},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6131128072738647},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6064474582672119},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6055949926376343},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5862746834754944},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5117813944816589},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4885326623916626},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.47910240292549133},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4713648855686188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42180532217025757},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4100644588470459},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15282276272773743},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.147001713514328},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07822364568710327},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07702481746673584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046197891235352},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7363752126693726},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6131128072738647},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6064474582672119},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6055949926376343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5862746834754944},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5117813944816589},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4885326623916626},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.47910240292549133},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4713648855686188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42180532217025757},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4100644588470459},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15282276272773743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.147001713514328},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07822364568710327},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07702481746673584},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1484210532","https://openalex.org/W1514535095","https://openalex.org/W1745334888","https://openalex.org/W2133564696","https://openalex.org/W2147527908","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2402144811","https://openalex.org/W2519224033","https://openalex.org/W2530876040","https://openalex.org/W2613904329","https://openalex.org/W2752782242","https://openalex.org/W2759071281","https://openalex.org/W2802023636","https://openalex.org/W2951527505","https://openalex.org/W2953384591","https://openalex.org/W2962826786","https://openalex.org/W2962998773","https://openalex.org/W2963266252","https://openalex.org/W2963403868","https://openalex.org/W2963495494","https://openalex.org/W2964036520","https://openalex.org/W2964265128","https://openalex.org/W2964308564","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6628927728","https://openalex.org/W6630875275","https://openalex.org/W6679434410","https://openalex.org/W6682137061","https://openalex.org/W6713134421","https://openalex.org/W6735593169","https://openalex.org/W6737778391","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2329500892","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W28991112"],"abstract_inverted_index":{"In":[0,21,43],"recent":[1],"years,":[2],"Residual":[3],"Networks":[4],"(ResNets)":[5],"have":[6],"significantly":[7],"increased":[8],"the":[9,26,34,56,75,77,88,134,139],"modeling":[10],"power":[11],"of":[12,28,36,74,112],"convolutional":[13],"neural":[14],"networks":[15],"(CNNs)":[16],"by":[17],"introducing":[18],"residual":[19],"connections.":[20],"this":[22],"paper,":[23],"we":[24,46],"explore":[25],"incorporation":[27],"spatial":[29,48,84,118],"and":[30,63,98,119,155,162],"channel":[31,105,120],"attention":[32,49,69,85,106,121],"into":[33],"structure":[35,54,137],"ResNets":[37],"for":[38,153],"noisy":[39,143],"speech":[40,146,152],"recognition":[41],"tasks.":[42],"our":[44],"experiments,":[45],"implemented":[47],"as":[50],"a":[51],"bottom-up":[52],"top-down":[53],"where":[55],"input":[57],"features":[58,80,97],"are":[59,81],"first":[60],"down":[61],"sampled":[62,66],"then":[64],"up":[65],"to":[67,92,94,109,127,141],"generate":[68],"maps.":[70,114],"At":[71],"each":[72],"block":[73],"ResNet,":[76],"generated":[78],"CNN":[79],"composed":[82],"with":[83,117],"maps":[86],"over":[87],"temporal-frequency":[89],"space,":[90],"learning":[91],"attend":[93],"salient":[95],"acoustic":[96],"suppress":[99,142],"noise.":[100],"Our":[101],"model":[102],"also":[103],"includes":[104],"that":[107,133],"attends":[108],"different":[110],"channels":[111],"feature":[113],"ResNet":[115],"blocks":[116],"modules":[122],"can":[123],"be":[124],"easily":[125],"stacked":[126],"construct":[128],"deeper":[129],"networks.":[130],"We":[131],"show":[132],"proposed":[135],"network":[136],"has":[138],"ability":[140],"signals":[144],"in":[145],"audio":[147],"without":[148],"requiring":[149],"parallel":[150],"clean":[151],"training,":[154],"achieve":[156],"promising":[157],"WER":[158],"reductions":[159],"on":[160],"CHiME2":[161],"CHiME3.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}