{"id":"https://openalex.org/W4392910569","doi":"https://doi.org/10.1109/icassp48485.2024.10445746","title":"Low Bitrate Loss Resilience Scheme for a Speech Enhancing Neural Codec","display_name":"Low Bitrate Loss Resilience Scheme for a Speech Enhancing Neural Codec","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392910569","doi":"https://doi.org/10.1109/icassp48485.2024.10445746"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5085365178","display_name":"Mihailo Kolund\u017eija","orcid":null},"institutions":[{"id":"https://openalex.org/I135428043","display_name":"Cisco Systems (United States)","ror":"https://ror.org/03yt1ez60","country_code":"US","type":"company","lineage":["https://openalex.org/I135428043"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mihailo Kolund\u017eija","raw_affiliation_strings":["Cisco Systems"],"affiliations":[{"raw_affiliation_string":"Cisco Systems","institution_ids":["https://openalex.org/I135428043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036017573","display_name":"Mathew Kavalekalam","orcid":null},"institutions":[{"id":"https://openalex.org/I135428043","display_name":"Cisco Systems (United States)","ror":"https://ror.org/03yt1ez60","country_code":"US","type":"company","lineage":["https://openalex.org/I135428043"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mathew Kavalekalam","raw_affiliation_strings":["Cisco Systems"],"affiliations":[{"raw_affiliation_string":"Cisco Systems","institution_ids":["https://openalex.org/I135428043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094180447","display_name":"Ivana Bali\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I135428043","display_name":"Cisco Systems (United States)","ror":"https://ror.org/03yt1ez60","country_code":"US","type":"company","lineage":["https://openalex.org/I135428043"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivana Bali\u0107","raw_affiliation_strings":["Cisco Systems"],"affiliations":[{"raw_affiliation_string":"Cisco Systems","institution_ids":["https://openalex.org/I135428043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319291","display_name":"Michelle Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I135428043","display_name":"Cisco Systems (United States)","ror":"https://ror.org/03yt1ez60","country_code":"US","type":"company","lineage":["https://openalex.org/I135428043"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michelle Mao","raw_affiliation_strings":["Cisco Systems"],"affiliations":[{"raw_affiliation_string":"Cisco Systems","institution_ids":["https://openalex.org/I135428043"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008307429","display_name":"R.A. Casas","orcid":null},"institutions":[{"id":"https://openalex.org/I135428043","display_name":"Cisco Systems (United States)","ror":"https://ror.org/03yt1ez60","country_code":"US","type":"company","lineage":["https://openalex.org/I135428043"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ra\u00fal Casas","raw_affiliation_strings":["Cisco Systems"],"affiliations":[{"raw_affiliation_string":"Cisco Systems","institution_ids":["https://openalex.org/I135428043"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085365178"],"corresponding_institution_ids":["https://openalex.org/I135428043"],"apc_list":null,"apc_paid":null,"fwci":0.375,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4971089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1031","last_page":"1035"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9997000098228455,"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":0.9987999796867371,"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":0.8510544300079346},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.8450853824615479},{"id":"https://openalex.org/keywords/packet-loss","display_name":"Packet loss","score":0.6321936845779419},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6059998869895935},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.5959165096282959},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.4997551441192627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49773815274238586},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.43897849321365356},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.43419957160949707},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.40469881892204285},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3851962387561798},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28063565492630005},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2127133309841156},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13212323188781738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510544300079346},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8450853824615479},{"id":"https://openalex.org/C54108766","wikidata":"https://www.wikidata.org/wiki/Q391064","display_name":"Packet loss","level":3,"score":0.6321936845779419},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6059998869895935},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.5959165096282959},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.4997551441192627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49773815274238586},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.43897849321365356},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.43419957160949707},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.40469881892204285},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3851962387561798},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28063565492630005},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2127133309841156},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13212323188781738},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1879918842","https://openalex.org/W2063142364","https://openalex.org/W2099040451","https://openalex.org/W2131738223","https://openalex.org/W2153623795","https://openalex.org/W2547875792","https://openalex.org/W2775336875","https://openalex.org/W2972519044","https://openalex.org/W3215615641","https://openalex.org/W4205788663","https://openalex.org/W4212774754","https://openalex.org/W4225287045","https://openalex.org/W4296069296","https://openalex.org/W4307323391","https://openalex.org/W4372190822","https://openalex.org/W4372348514","https://openalex.org/W4377231659","https://openalex.org/W4385245566","https://openalex.org/W4385823256","https://openalex.org/W6639363673","https://openalex.org/W6718379498","https://openalex.org/W6729448088","https://openalex.org/W6781251213","https://openalex.org/W6798098866","https://openalex.org/W6798193259"],"related_works":["https://openalex.org/W2374470469","https://openalex.org/W2129913000","https://openalex.org/W2899318368","https://openalex.org/W2370747337","https://openalex.org/W2363660481","https://openalex.org/W2352448339","https://openalex.org/W2159899134","https://openalex.org/W2787189739","https://openalex.org/W137020845","https://openalex.org/W3095556352"],"abstract_inverted_index":{"Deep":[0],"neural":[1,74],"networks":[2],"have":[3],"proven":[4],"their":[5],"efficacy":[6],"in":[7,22],"encoding":[8],"high-quality":[9],"speech":[10,35,75,89],"and":[11,36,91,101,150,158],"audio":[12,23,37,135],"at":[13,153],"remarkably":[14],"low":[15],"bitrates,":[16],"while":[17],"also":[18],"demonstrating":[19],"superior":[20],"performance":[21],"packet":[24,102,119],"loss":[25,103,120],"concealment":[26],"(PLC)":[27],"compared":[28],"to":[29,51,93],"traditional":[30],"methods.":[31],"Although":[32],"ultra":[33],"low-bitrate":[34,88,112,133],"codecs":[38],"may":[39],"appear":[40],"less":[41],"practical":[42],"for":[43,59,115,132],"real-time":[44],"voice":[45,62],"communication":[46,63],"over":[47],"the":[48,140,143,148],"Internet":[49],"due":[50],"packetization":[52],"overhead,":[53],"they":[54],"present":[55,109],"a":[56,73,80,110,125],"promising":[57],"solution":[58],"ensuring":[60],"uninterrupted":[61],"under":[64],"adverse":[65,156],"network":[66,159],"conditions.":[67,160],"In":[68],"this":[69,106],"paper,":[70],"we":[71,108,138],"use":[72],"codec":[76],"designed":[77,131],"end-to-end,":[78],"encompassing":[79],"versatile":[81],"set":[82],"of":[83,142],"features":[84],"ranging":[85],"from":[86,117],"efficient":[87],"coding":[90,128],"decoding":[92],"advanced":[94],"functionalities":[95],"such":[96],"as":[97],"noise":[98],"removal,":[99],"dereverberation,":[100],"concealment.":[104],"For":[105],"codec,":[107,145],"long":[111],"redundancy":[113],"mechanism":[114],"recovering":[116],"extended":[118],"bursts.":[121],"We":[122],"furthermore":[123],"introduce":[124],"memory-efficient":[126],"entropy":[127],"scheme":[129],"specifically":[130],"redundant":[134],"packets.":[136],"Finally,":[137],"demonstrate":[139],"effectiveness":[141],"said":[144],"together":[146],"with":[147,155],"memory-":[149],"bitrate-efficient":[151],"redundancy,":[152],"coping":[154],"acoustic":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
