{"id":"https://openalex.org/W4226055090","doi":"https://doi.org/10.1109/asru51503.2021.9687902","title":"ChannelAugment: Improving Generalization of Multi-Channel ASR by Training with Input Channel Randomization","display_name":"ChannelAugment: Improving Generalization of Multi-Channel ASR by Training with Input Channel Randomization","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4226055090","doi":"https://doi.org/10.1109/asru51503.2021.9687902"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687902","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5050683447","display_name":"Marco Gaudesi","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Marco Gaudesi","raw_affiliation_strings":["Nuance Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Felix Weninger","raw_affiliation_strings":["Nuance Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108774400","display_name":"Dushyant Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":["Nuance Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109588257","display_name":"Puming Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Puming Zhan","raw_affiliation_strings":["Nuance Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications","institution_ids":["https://openalex.org/I1292318990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1721,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46361186,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"824","last_page":"829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7700068950653076},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7354100942611694},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6389113664627075},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4766426980495453},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44271039962768555},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4311589002609253},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.43031567335128784},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35584595799446106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24164265394210815},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13852983713150024},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1194077730178833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7700068950653076},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7354100942611694},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6389113664627075},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4766426980495453},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44271039962768555},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4311589002609253},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.43031567335128784},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35584595799446106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24164265394210815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13852983713150024},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1194077730178833},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687902","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2057035781","https://openalex.org/W2117678320","https://openalex.org/W2133564696","https://openalex.org/W2134533334","https://openalex.org/W2168729028","https://openalex.org/W2327501763","https://openalex.org/W2398042854","https://openalex.org/W2512137286","https://openalex.org/W2517616541","https://openalex.org/W2589857635","https://openalex.org/W2622203030","https://openalex.org/W2759921250","https://openalex.org/W2767071179","https://openalex.org/W2921214093","https://openalex.org/W2921496354","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2962780374","https://openalex.org/W2962970794","https://openalex.org/W2964391865","https://openalex.org/W2972686261","https://openalex.org/W2972799770","https://openalex.org/W2972991469","https://openalex.org/W2983061588","https://openalex.org/W3002595344","https://openalex.org/W3008191852","https://openalex.org/W3008762051","https://openalex.org/W3015527782","https://openalex.org/W3015889230","https://openalex.org/W3015995734","https://openalex.org/W3016010032","https://openalex.org/W3024388846","https://openalex.org/W3036800705","https://openalex.org/W3096273170","https://openalex.org/W3097747488","https://openalex.org/W3097777922","https://openalex.org/W3117722298","https://openalex.org/W6638749077","https://openalex.org/W6679434410","https://openalex.org/W6759957882","https://openalex.org/W6763847309","https://openalex.org/W6766096327","https://openalex.org/W6767672098","https://openalex.org/W6780021897","https://openalex.org/W6787857153"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918","https://openalex.org/W2770593030"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"multi-channel":[2,17,103],"ASR":[3,10,22],"systems":[4,29,65],"show":[5],"state-of-the-art":[6],"performance":[7],"in":[8,48,56,66,101,108,126,185],"far-field":[9],"tasks":[11],"by":[12],"joint":[13],"training":[14,186],"of":[15,27,137,175,191],"a":[16,39,51,87,138,181],"front-end":[18],"along":[19],"with":[20,36],"the":[21,102,112,147],"model.":[23],"The":[24],"main":[25],"limitation":[26],"such":[28],"is":[30,54,70,95],"that":[31],"they":[32],"are":[33],"usually":[34],"trained":[35],"data":[37,91],"from":[38],"fixed":[40],"array":[41,53,80,116,170],"geometry,":[42],"which":[43,94,131],"can":[44],"lead":[45],"to":[46,62,72,110,114,128,146],"degradation":[47,190],"accuracy":[49],"when":[50],"different":[52,76,173],"used":[55],"testing.":[57],"This":[58],"makes":[59],"it":[60,69],"challenging":[61],"deploy":[63,75],"these":[64],"practice,":[67],"as":[68],"costly":[71],"retrain":[73],"and":[74,89,151],"models":[77],"for":[78],"various":[79,115,169],"configurations.":[81],"To":[82],"address":[83],"this,":[84],"we":[85,162,179],"present":[86],"simple":[88],"effective":[90],"augmentation":[92],"technique,":[93],"based":[96],"on":[97],"randomly":[98],"dropping":[99],"channels":[100],"audio":[104],"input":[105,141],"during":[106],"training,":[107],"order":[109],"improve":[111],"robustness":[113],"configurations":[117,171],"at":[118],"test":[119],"time.":[120],"We":[121,143],"call":[122],"this":[123],"technique":[124],"ChannelAugment,":[125],"contrast":[127],"SpecAugment":[129],"(SA)":[130],"drops":[132],"time":[133,187],"and/or":[134],"frequency":[135],"components":[136],"single":[139],"channel":[140],"au-dio.":[142],"apply":[144],"ChannelAugment":[145],"Spatial":[148],"Filtering":[149],"(SF)":[150],"Minimum":[152],"Variance":[153],"Distortionless":[154],"Response":[155],"(MVDR)":[156],"neural":[157],"beam-forming":[158],"approaches.":[159],"For":[160,177],"SF,":[161],"observe":[163],"10.6":[164],"%":[165,183],"WER":[166],"improvement":[167],"across":[168],"employing":[172],"numbers":[174],"microphones.":[176],"MVDR,":[178],"achieve":[180],"74":[182],"reduction":[184],"without":[188],"causing":[189],"recognition":[192],"accuracy.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}