{"id":"https://openalex.org/W3004928994","doi":"https://doi.org/10.1109/icassp40776.2020.9053940","title":"Robust Multi-Channel Speech Recognition Using Frequency Aligned Network","display_name":"Robust Multi-Channel Speech Recognition Using Frequency Aligned Network","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3004928994","doi":"https://doi.org/10.1109/icassp40776.2020.9053940","mag":"3004928994"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.02520","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101511624","display_name":"Taejin Park","orcid":"https://orcid.org/0000-0003-2040-5884"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Taejin Park","raw_affiliation_strings":["University of Southern California (USC),Los Angeles,CA,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California (USC),Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053915317","display_name":"Kenichi Kumatani","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenichi Kumatani","raw_affiliation_strings":["Amazon Inc,Sunnyvale,CA,USA","[Amazon Inc, Sunnyvale, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Amazon Inc,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon Inc, Sunnyvale, CA, USA]","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060740546","display_name":"Minhua Wu","orcid":"https://orcid.org/0000-0001-9798-2984"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minhua Wu","raw_affiliation_strings":["Amazon Inc,Sunnyvale,CA,USA","[Amazon Inc, Sunnyvale, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Amazon Inc,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon Inc, Sunnyvale, CA, USA]","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113697636","display_name":"Shiva Sundaram","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiva Sundaram","raw_affiliation_strings":["Amazon Inc,Sunnyvale,CA,USA","[Amazon Inc, Sunnyvale, CA, USA]"],"affiliations":[{"raw_affiliation_string":"Amazon Inc,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon Inc, Sunnyvale, CA, USA]","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101511624"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01440168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6859","last_page":"6863"},"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":0.9995999932289124,"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":0.9994000196456909,"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":0.7069482803344727},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.6232731938362122},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5840054154396057},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5820015668869019},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5277645587921143},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5047365427017212},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24364212155342102},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16227614879608154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069482803344727},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.6232731938362122},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5840054154396057},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5820015668869019},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5277645587921143},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5047365427017212},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24364212155342102},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16227614879608154},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.02520","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.02520","pdf_url":"https://arxiv.org/pdf/2002.02520","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3004928994","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.02520.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2002.02520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.02520","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/5g61-c208","is_oa":true,"landing_page_url":"https://doi.org/10.17023/5g61-c208","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.02520","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.02520","pdf_url":"https://arxiv.org/pdf/2002.02520","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3004928994.pdf","grobid_xml":"https://content.openalex.org/works/W3004928994.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1982728343","https://openalex.org/W2015433306","https://openalex.org/W2041768951","https://openalex.org/W2103088716","https://openalex.org/W2113556376","https://openalex.org/W2129227482","https://openalex.org/W2156201704","https://openalex.org/W2264763718","https://openalex.org/W2398972335","https://openalex.org/W2405578611","https://openalex.org/W2515439472","https://openalex.org/W2600628583","https://openalex.org/W2787752687","https://openalex.org/W2889367162","https://openalex.org/W2890553422","https://openalex.org/W2891997645","https://openalex.org/W2921214093","https://openalex.org/W2921496354","https://openalex.org/W2952696100","https://openalex.org/W6683234268","https://openalex.org/W6693093084","https://openalex.org/W6713835734","https://openalex.org/W6735168207"],"related_works":["https://openalex.org/W2921496354","https://openalex.org/W2952696100","https://openalex.org/W2808797590","https://openalex.org/W3170088519","https://openalex.org/W2564013664","https://openalex.org/W3102070904","https://openalex.org/W2465697055","https://openalex.org/W2787069756","https://openalex.org/W3186318461","https://openalex.org/W2398042854","https://openalex.org/W2970789614","https://openalex.org/W2945926039","https://openalex.org/W2904310189","https://openalex.org/W2363736995","https://openalex.org/W3174609245","https://openalex.org/W2594225660","https://openalex.org/W2787292435","https://openalex.org/W2888907095","https://openalex.org/W3095507987","https://openalex.org/W3111246190"],"abstract_inverted_index":{"Conventional":[0],"speech":[1,12,54],"enhancement":[2],"technique":[3],"such":[4],"as":[5],"beamforming":[6],"has":[7,22],"known":[8],"benefits":[9],"for":[10,50],"far-field":[11,114],"recognition.":[13],"Our":[14],"own":[15],"work":[16],"in":[17,61,90,124,146],"frequency-domain":[18],"multi-channel":[19,52,132],"acoustic":[20,35,126,133],"modeling":[21],"shown":[23],"additional":[24],"improvements":[25],"by":[26],"training":[27],"a":[28,136],"spatial":[29],"filtering":[30],"layer":[31,60],"jointly":[32],"within":[33],"an":[34,58,121],"model.":[36],"In":[37],"this":[38,43,81],"paper,":[39],"we":[40],"further":[41],"develop":[42],"idea":[44],"and":[45,96],"use":[46],"frequency":[47,63,67,72,76,105,137],"aligned":[48,68,106,138],"network":[49,107,139],"robust":[51],"automatic":[53],"recognition":[55],"(ASR).":[56],"Unlike":[57],"affine":[59],"the":[62,65,86,91,98,112],"domain,":[64],"proposed":[66],"component":[69],"prevents":[70],"one":[71],"bin":[73],"influencing":[74],"other":[75],"bins.":[77],"We":[78,101,128],"show":[79,129],"that":[80,130],"modification":[82],"not":[83],"only":[84],"reduces":[85],"number":[87],"of":[88,104],"parameters":[89],"model":[92,134],"but":[93],"also":[94],"significantly":[95],"improves":[97],"ASR":[99,109,122],"performance.":[100],"investigate":[102],"effects":[103],"through":[108],"experiments":[110],"on":[111],"real-world":[113],"data":[115],"where":[116],"users":[117],"are":[118],"interacting":[119],"with":[120,135],"system":[123],"uncontrolled":[125],"environments.":[127],"our":[131],"shows":[140],"up":[141],"to":[142],"18%":[143],"relative":[144],"reduction":[145],"word":[147],"error":[148],"rate.":[149]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}