{"id":"https://openalex.org/W3011666502","doi":"https://doi.org/10.1109/sips47522.2019.9020406","title":"SIR Beam Selector for Amazon Echo Devices Audio Front-End","display_name":"SIR Beam Selector for Amazon Echo Devices Audio Front-End","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W3011666502","doi":"https://doi.org/10.1109/sips47522.2019.9020406","mag":"3011666502"},"language":"en","primary_location":{"id":"doi:10.1109/sips47522.2019.9020406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips47522.2019.9020406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Workshop on Signal Processing Systems (SiPS)","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/A5082681724","display_name":"Xianxian Zhang","orcid":"https://orcid.org/0000-0003-1238-1341"},"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":"Xianxian Zhang","raw_affiliation_strings":["Amazon Inc., Sunnyvale, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc., Sunnyvale, California, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075577786","display_name":"Trausti Kristjansson","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":"Trausti Kristjansson","raw_affiliation_strings":["Amazon Inc., Sunnyvale, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc., Sunnyvale, California, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048547719","display_name":"Philip Hilmes","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":"Philip Hilmes","raw_affiliation_strings":["Amazon Inc., Sunnyvale, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Inc., Sunnyvale, California, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21009046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"302","last_page":"306"},"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/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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/echo","display_name":"Echo (communications protocol)","score":0.7326467633247375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6393696069717407},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.628801703453064},{"id":"https://openalex.org/keywords/beam","display_name":"Beam (structure)","score":0.5885187387466431},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5723098516464233},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5602721571922302},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5378605127334595},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5198231935501099},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.49885129928588867},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4717472493648529},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4705389142036438},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.41336822509765625},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2719741463661194},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.20920449495315552},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1967143416404724},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.17114192247390747},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1493189036846161},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.143662691116333}],"concepts":[{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.7326467633247375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6393696069717407},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.628801703453064},{"id":"https://openalex.org/C168834538","wikidata":"https://www.wikidata.org/wiki/Q3705329","display_name":"Beam (structure)","level":2,"score":0.5885187387466431},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5723098516464233},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5602721571922302},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5378605127334595},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5198231935501099},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.49885129928588867},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4717472493648529},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4705389142036438},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.41336822509765625},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2719741463661194},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.20920449495315552},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1967143416404724},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.17114192247390747},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1493189036846161},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.143662691116333},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sips47522.2019.9020406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips47522.2019.9020406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Workshop on Signal Processing Systems (SiPS)","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":14,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W1847628149","https://openalex.org/W1977167953","https://openalex.org/W2060108923","https://openalex.org/W2101609516","https://openalex.org/W2109199922","https://openalex.org/W2110075977","https://openalex.org/W2111320049","https://openalex.org/W2144244295","https://openalex.org/W2167584817","https://openalex.org/W2168729028","https://openalex.org/W2903055733","https://openalex.org/W4206633762","https://openalex.org/W4249052411"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2041060376","https://openalex.org/W2963983801","https://openalex.org/W3119734852"],"abstract_inverted_index":{"The":[0],"Audio":[1],"Front-End":[2],"(AFE)":[3],"is":[4,31,109],"a":[5,49,85,94],"key":[6],"component":[7,27],"in":[8],"mitigating":[9],"acoustic":[10],"environmental":[11],"challenges":[12],"for":[13,75,118],"far-field":[14],"automatic":[15],"speech":[16,119],"recognition":[17,120],"(ASR)":[18],"on":[19],"Amazon":[20],"Echo":[21],"family":[22],"of":[23,28,63,84],"products.":[24],"A":[25],"critical":[26],"the":[29,32,41,61,64,71,82,101],"AFE":[30,78],"Beam":[33],"Selector,":[34],"which":[35,37],"identifies":[36],"beam":[38,52,72,91,98],"points":[39],"to":[40,59,87,96,113,123,133],"target":[42],"user.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47],"proposed":[48],"new":[50],"SIR":[51],"selector":[53,92,99],"that":[54],"utilizes":[55],"subband-based":[56],"signal-to-interference":[57],"ratios":[58],"learn":[60],"locations":[62],"audio":[65],"sources":[66],"and":[67,111,125],"therefore":[68],"further":[69],"improve":[70,126],"selection":[73],"accuracy":[74],"multi-microphone":[76],"based":[77],"system.":[79],"We":[80],"analyzed":[81],"performance":[83,128],"Signal":[86],"Interference":[88],"Ratio":[89],"(SIR)":[90],"with":[93],"comparison":[95],"classic":[97],"using":[100],"datasets":[102],"collected":[103],"under":[104],"various":[105],"conditions.":[106],"This":[107],"method":[108],"evaluated":[110],"shown":[112],"simultaneously":[114],"decrease":[115],"word-error-rate":[116],"(WER)":[117],"by":[121,131],"up":[122,132],"46.20%":[124],"barge-in":[127],"via":[129],"FRR":[130],"39.18%.":[134]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}