{"id":"https://openalex.org/W3166265383","doi":"https://doi.org/10.21437/interspeech.2021-1214","title":"Multi-Channel Opus Compression for Far-Field Automatic Speech Recognition with a Fixed Bitrate Budget","display_name":"Multi-Channel Opus Compression for Far-Field Automatic Speech Recognition with a Fixed Bitrate Budget","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3166265383","doi":"https://doi.org/10.21437/interspeech.2021-1214","mag":"3166265383"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1214","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/2106.07994","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011191228","display_name":"Lukas Drude","orcid":"https://orcid.org/0000-0003-3683-5432"},"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":"Lukas Drude","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006131416","display_name":"Jahn Heymann","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":"Jahn Heymann","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015722753","display_name":"Andreas Schwarz","orcid":"https://orcid.org/0000-0001-5484-3976"},"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":"Andreas Schwarz","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05637009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1669","last_page":"1673"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.7643107771873474},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6810474395751953},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4869631230831146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4525439739227295},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.44581204652786255},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.329123854637146},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2393714189529419},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.229844331741333},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21291333436965942},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1378210484981537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7643107771873474},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6810474395751953},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4869631230831146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4525439739227295},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.44581204652786255},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.329123854637146},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2393714189529419},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.229844331741333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21291333436965942},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1378210484981537}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1214","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.07994","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.07994","pdf_url":"https://arxiv.org/pdf/2106.07994","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":null,"raw_type":"text"},{"id":"mag:3166265383","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.07994.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.2106.07994","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.07994","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.07994","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.07994","pdf_url":"https://arxiv.org/pdf/2106.07994","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3166265383.pdf","grobid_xml":"https://content.openalex.org/works/W3166265383.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1486749116","https://openalex.org/W1575718033","https://openalex.org/W1828163288","https://openalex.org/W1885680957","https://openalex.org/W1966264494","https://openalex.org/W1985242443","https://openalex.org/W2013020033","https://openalex.org/W2037769258","https://openalex.org/W2042860487","https://openalex.org/W2060108923","https://openalex.org/W2138880468","https://openalex.org/W2157819213","https://openalex.org/W2160525176","https://openalex.org/W2164538846","https://openalex.org/W2398042854","https://openalex.org/W2406280060","https://openalex.org/W2517616541","https://openalex.org/W2559809918","https://openalex.org/W2589857635","https://openalex.org/W2622203030","https://openalex.org/W2746902340","https://openalex.org/W2785871231","https://openalex.org/W2921214093","https://openalex.org/W2952696100","https://openalex.org/W2963122170","https://openalex.org/W2982471419","https://openalex.org/W3003448205","https://openalex.org/W3015995734","https://openalex.org/W3086154751"],"related_works":["https://openalex.org/W3197480135","https://openalex.org/W2117374786","https://openalex.org/W2138573630","https://openalex.org/W2023061457","https://openalex.org/W2122510603","https://openalex.org/W3143821920","https://openalex.org/W2126349228","https://openalex.org/W2151426891","https://openalex.org/W1988953538","https://openalex.org/W2024674850","https://openalex.org/W2143211266","https://openalex.org/W128370044","https://openalex.org/W2119411420","https://openalex.org/W2542586858","https://openalex.org/W2996780790","https://openalex.org/W2124542312","https://openalex.org/W409458924","https://openalex.org/W2045240876","https://openalex.org/W3177376120","https://openalex.org/W2059171637"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"in":[4,128,144,188],"the":[5,8,33,36,52,81,90,101,129,133,136,140,151],"cloud":[6],"allows":[7],"use":[9],"of":[10,35,44,85,103,135],"larger":[11],"models":[12],"and":[13,83,117,149],"more":[14],"powerful":[15],"multi-channel":[16,76,121,145,158],"signal":[17],"processing":[18],"front-ends":[19],"compared":[20],"to":[21,32,50,80,125,168],"on-device":[22],"processing.":[23],"However,":[24,66],"it":[25],"also":[26],"adds":[27],"an":[28,97],"inherent":[29],"latency":[30],"due":[31,79],"transmission":[34],"audio":[37],"signal,":[38],"especially":[39,74],"when":[40],"transmitting":[41],"multiple":[42],"channels":[43],"a":[45,60,71,111,120,157,169,175,184,189],"microphone":[46,104],"array.":[47],"One":[48],"way":[49],"reduce":[51,126],"network":[53],"bandwidth":[54],"requirements":[55],"is":[56],"client-side":[57],"compression":[58,68,102],"with":[59,156],"lossy":[61],"codec":[62],"such":[63],"as":[64],"Opus.":[65],"this":[67,93],"can":[69,166],"have":[70],"detrimental":[72],"effect":[73,134],"on":[75,108,139,153],"ASR":[77,155],"front-ends,":[78],"distortion":[82],"loss":[84],"spatial":[86,122,141],"information":[87,142],"introduced":[88],"by":[89],"codec.":[91],"In":[92],"publication,":[94],"we":[95],"propose":[96],"improved":[98],"approach":[99,116,138,165],"for":[100,183],"array":[105],"signals":[106,146],"based":[107],"Opus,":[109],"using":[110],"modified":[112],"joint":[113],"channel":[114,191],"coding":[115],"additionally":[118],"introducing":[119],"decorrelating":[123],"transform":[124],"redundancy":[127],"transmission.":[130],"We":[131,161],"illustrate":[132],"proposed":[137],"retained":[143],"after":[147],"compression,":[148],"evaluate":[150],"performance":[152],"far-field":[154],"beamforming":[159],"front-end.":[160],"demonstrate":[162],"that":[163],"our":[164],"lead":[167],"37.5":[170],"%":[171,177],"bitrate":[172,186],"reduction":[173,182],"or":[174],"5.1":[176],"relative":[178],"word":[179],"error":[180],"rate":[181],"fixed":[185],"budget":[187],"seven":[190],"setup.":[192]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
