{"id":"https://openalex.org/W3132710062","doi":"https://doi.org/10.1109/icassp39728.2021.9414605","title":"Enhancing into the Codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders","display_name":"Enhancing into the Codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3132710062","doi":"https://doi.org/10.1109/icassp39728.2021.9414605","mag":"3132710062"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/2102.06610","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014125577","display_name":"Jonah Casebeer","orcid":"https://orcid.org/0000-0002-8741-9773"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jonah Casebeer","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","***University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"***University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023897626","display_name":"Vinjai Vale","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinjai Vale","raw_affiliation_strings":["Stanford University","Stanford University ()"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036092393","display_name":"Umut Isik","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":"Umut Isik","raw_affiliation_strings":["Amazon Web Services","[Amazon Web Services]"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon Web Services]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"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":"Jean-Marc Valin","raw_affiliation_strings":["Amazon Web Services","[Amazon Web Services]"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon Web Services]","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091775011","display_name":"Ritwik Giri","orcid":"https://orcid.org/0000-0002-8599-3229"},"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":"Ritwik Giri","raw_affiliation_strings":["Amazon Web Services","[Amazon Web Services]"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon Web Services]","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112751528","display_name":"Arvindh Krishnaswamy","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":"Arvindh Krishnaswamy","raw_affiliation_strings":["Amazon Web Services","[Amazon Web Services]"],"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"[Amazon Web Services]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5014125577"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.3078,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51100967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"711","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.719994068145752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7131209373474121},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6447033882141113},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6364058256149292},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6051194667816162},{"id":"https://openalex.org/keywords/gas-compressor","display_name":"Gas compressor","score":0.5034279227256775},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.499387264251709},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4561951756477356},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4457816481590271},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31920677423477173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3143935203552246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10030895471572876},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09466114640235901},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07439190149307251}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.719994068145752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7131209373474121},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6447033882141113},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6364058256149292},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6051194667816162},{"id":"https://openalex.org/C131097465","wikidata":"https://www.wikidata.org/wiki/Q178898","display_name":"Gas compressor","level":2,"score":0.5034279227256775},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.499387264251709},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4561951756477356},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4457816481590271},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31920677423477173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3143935203552246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10030895471572876},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09466114640235901},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07439190149307251},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.06610","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06610","pdf_url":"https://arxiv.org/pdf/2102.06610","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3132710062","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.06610","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.2102.06610","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.06610","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/75cz-vt87","is_oa":true,"landing_page_url":"https://doi.org/10.17023/75cz-vt87","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:2102.06610","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.06610","pdf_url":"https://arxiv.org/pdf/2102.06610","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3132710062.pdf","grobid_xml":"https://content.openalex.org/works/W3132710062.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1885680957","https://openalex.org/W1897240248","https://openalex.org/W2044893557","https://openalex.org/W2396130155","https://openalex.org/W2593116425","https://openalex.org/W2752796333","https://openalex.org/W2757519008","https://openalex.org/W2775336875","https://openalex.org/W2935711438","https://openalex.org/W2949382160","https://openalex.org/W2954386831","https://openalex.org/W2963091184","https://openalex.org/W2963799213","https://openalex.org/W2963868408","https://openalex.org/W2972519044","https://openalex.org/W3016098186","https://openalex.org/W3049206033","https://openalex.org/W3097034112","https://openalex.org/W3097692357","https://openalex.org/W3100270690","https://openalex.org/W3110277971","https://openalex.org/W3125709657","https://openalex.org/W6639363673","https://openalex.org/W6712634873"],"related_works":["https://openalex.org/W2504881501","https://openalex.org/W1966551546","https://openalex.org/W3016098186","https://openalex.org/W2408382539","https://openalex.org/W1613096649","https://openalex.org/W2973045486","https://openalex.org/W2145000270","https://openalex.org/W2122551512","https://openalex.org/W1522381657","https://openalex.org/W2950237361","https://openalex.org/W3131354345","https://openalex.org/W1970272279","https://openalex.org/W127789313","https://openalex.org/W2734689285","https://openalex.org/W2162551712","https://openalex.org/W2125175190","https://openalex.org/W1654345096","https://openalex.org/W3149951309","https://openalex.org/W2393429130","https://openalex.org/W2804178227"],"abstract_inverted_index":{"Audio":[0],"codecs":[1],"based":[2],"on":[3,41,72,82],"discretized":[4],"neural":[5],"autoencoders":[6,43],"have":[7],"recently":[8],"been":[9],"developed":[10],"and":[11,33,51,54],"shown":[12],"to":[13],"provide":[14],"significantly":[15],"higher":[16],"compression":[17],"levels":[18],"for":[19],"comparable":[20],"quality":[21],"speech":[22,31,74],"out-put.":[23],"However,":[24],"these":[25],"models":[26],"are":[27],"tightly":[28],"coupled":[29],"with":[30,44],"content,":[32],"produce":[34],"unintended":[35],"outputs":[36],"in":[37,60],"noisy":[38,61],"conditions.":[39,62],"Based":[40],"VQ-VAE":[42],"WaveRNN":[45],"decoders,":[46,53],"we":[47],"develop":[48],"compressor-enhancer":[49,68],"encoders":[50],"accompanying":[52],"show":[55],"that":[56,66],"they":[57],"operate":[58],"well":[59],"We":[63],"also":[64],"observe":[65],"a":[67,77],"model":[69,79],"performs":[70],"better":[71],"clean":[73,83],"inputs":[75],"than":[76],"compressor":[78],"trained":[80],"only":[81],"speech.":[84]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}