{"id":"https://openalex.org/W4372190822","doi":"https://doi.org/10.1109/icassp49357.2023.10096528","title":"Low-Bitrate Redundancy Coding of Speech Using A Rate-Distortion-Optimized Variational Autoencoder","display_name":"Low-Bitrate Redundancy Coding of Speech Using A Rate-Distortion-Optimized Variational Autoencoder","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372190822","doi":"https://doi.org/10.1109/icassp49357.2023.10096528"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096528","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042244085","display_name":"Jan B\u00fcthe","orcid":"https://orcid.org/0000-0001-5872-4325"},"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":"Jan B\u00fcthe","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110745444","display_name":"Ahmed Mustafa","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":"Ahmed Mustafa","raw_affiliation_strings":["Amazon Web Services,Palo Alto,USA","Amazon Web Services, Palo Alto, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services,Palo Alto,USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Web Services, Palo Alto, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6629,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84455862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.7484564781188965},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.663018524646759},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6324388980865479},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5665158033370972},{"id":"https://openalex.org/keywords/packet-loss","display_name":"Packet loss","score":0.5181399583816528},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5164046883583069},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4888302683830261},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.4433537721633911},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4410174489021301},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3133885860443115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2922855019569397},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1797492504119873},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12443828582763672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484564781188965},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.663018524646759},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6324388980865479},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5665158033370972},{"id":"https://openalex.org/C54108766","wikidata":"https://www.wikidata.org/wiki/Q391064","display_name":"Packet loss","level":3,"score":0.5181399583816528},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5164046883583069},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4888302683830261},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.4433537721633911},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4410174489021301},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3133885860443115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2922855019569397},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1797492504119873},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12443828582763672},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096528","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1879918842","https://openalex.org/W1959608418","https://openalex.org/W2063678710","https://openalex.org/W2151912295","https://openalex.org/W2242818861","https://openalex.org/W2750167318","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2895654193","https://openalex.org/W2963091184","https://openalex.org/W2963208781","https://openalex.org/W2963799213","https://openalex.org/W2964199361","https://openalex.org/W2972519044","https://openalex.org/W3025844872","https://openalex.org/W3028785944","https://openalex.org/W3028954259","https://openalex.org/W3030374183","https://openalex.org/W3032558098","https://openalex.org/W3092791109","https://openalex.org/W3095497211","https://openalex.org/W3160576174","https://openalex.org/W3172592779","https://openalex.org/W3198020407","https://openalex.org/W3215615641","https://openalex.org/W4205788663","https://openalex.org/W4225290925","https://openalex.org/W4296069296","https://openalex.org/W4297841420","https://openalex.org/W6639363673","https://openalex.org/W6640963894","https://openalex.org/W6690026940","https://openalex.org/W6755853340","https://openalex.org/W6760712927","https://openalex.org/W6777781272","https://openalex.org/W6778625279","https://openalex.org/W6779192484","https://openalex.org/W6793364766","https://openalex.org/W6798098866"],"related_works":["https://openalex.org/W2825911253","https://openalex.org/W2068722902","https://openalex.org/W2601778967","https://openalex.org/W2904248843","https://openalex.org/W1567783810","https://openalex.org/W2163066683","https://openalex.org/W1594363840","https://openalex.org/W2348615440","https://openalex.org/W4293241800","https://openalex.org/W2121468461"],"abstract_inverted_index":{"Robustness":[0],"to":[1,27,70,84],"packet":[2,16],"loss":[3,17],"is":[4,43,53,98],"one":[5],"of":[6,75],"the":[7,49,95,102,109],"main":[8],"ongoing":[9],"challenges":[10],"in":[11,48],"real-time":[12],"speech":[13,66],"communication.":[14],"Deep":[15],"concealment":[18],"(PLC)":[19],"techniques":[20,34],"have":[21],"recently":[22],"demonstrated":[23],"improved":[24],"quality":[25],"compared":[26],"traditional":[28],"PLC.":[29],"Despite":[30],"that,":[31],"all":[32],"PLC":[33],"hit":[35],"fundamental":[36],"limitations":[37],"when":[38],"too":[39],"much":[40],"acoustic":[41],"information":[42],"lost.":[44],"To":[45],"reduce":[46],"losses":[47],"first":[50],"place,":[51],"data":[52],"commonly":[54],"sent":[55],"multiple":[56],"times":[57],"using":[58,87],"various":[59],"redundancy":[60,77,86,97],"mechanisms.":[61],"We":[62],"propose":[63],"a":[64,72,79],"neural":[65],"coder":[67],"specifically":[68],"optimized":[69],"transmit":[71],"large":[73],"amount":[74],"overlapping":[76],"at":[78],"very":[80],"low":[81],"bitrate,":[82],"up":[83],"50x":[85],"less":[88],"than":[89,101],"32":[90],"kb/s.":[91],"Results":[92],"show":[93],"that":[94,108],"proposed":[96],"more":[99],"effective":[100],"existing":[103],"Opus":[104],"codec":[105],"redundancy,":[106],"and":[107],"two":[110],"can":[111],"be":[112],"combined":[113],"for":[114],"even":[115],"greater":[116],"robustness.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
