{"id":"https://openalex.org/W4206534210","doi":"https://doi.org/10.1109/lsp.2021.3132557","title":"Neurally Optimized Decoder for Low Bitrate Speech Codec","display_name":"Neurally Optimized Decoder for Low Bitrate Speech Codec","publication_year":2021,"publication_date":"2021-12-03","ids":{"openalex":"https://openalex.org/W4206534210","doi":"https://doi.org/10.1109/lsp.2021.3132557"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3132557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3132557","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5068972361","display_name":"Hyung Yong Kim","orcid":"https://orcid.org/0000-0001-6009-9530"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyung Yong Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016783920","display_name":"Ji Won Yoon","orcid":"https://orcid.org/0000-0001-8631-4489"},"institutions":[{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]},{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ji Won Yoon","raw_affiliation_strings":["Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102984975","display_name":"Won Ik Cho","orcid":"https://orcid.org/0000-0002-8882-9125"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Won Ik Cho","raw_affiliation_strings":["Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068972361"],"corresponding_institution_ids":["https://openalex.org/I139264467","https://openalex.org/I4210164379"],"apc_list":null,"apc_paid":null,"fwci":0.4571,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6356998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"29","issue":null,"first_page":"244","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.9212559461593628},{"id":"https://openalex.org/keywords/bitstream","display_name":"Bitstream","score":0.900121808052063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7940163016319275},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7743571996688843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6713098287582397},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.553112804889679},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.5212807655334473},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4161718189716339},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.3284221887588501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2894176244735718},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23065143823623657},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1420217752456665}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.9212559461593628},{"id":"https://openalex.org/C136695289","wikidata":"https://www.wikidata.org/wiki/Q415568","display_name":"Bitstream","level":3,"score":0.900121808052063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940163016319275},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7743571996688843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6713098287582397},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.553112804889679},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.5212807655334473},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4161718189716339},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.3284221887588501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2894176244735718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23065143823623657},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1420217752456665}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2021.3132557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3132557","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W2108532241","https://openalex.org/W2125389028","https://openalex.org/W2165291881","https://openalex.org/W2519091744","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2935711438","https://openalex.org/W2972519044","https://openalex.org/W2981728663","https://openalex.org/W3016098186","https://openalex.org/W4210849719","https://openalex.org/W4385245566","https://openalex.org/W6678815747","https://openalex.org/W6739901393","https://openalex.org/W6748409065"],"related_works":["https://openalex.org/W2374470469","https://openalex.org/W2159899134","https://openalex.org/W2509918616","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W2060409740","https://openalex.org/W2352448339","https://openalex.org/W2010376816","https://openalex.org/W1542588102","https://openalex.org/W1000239413"],"abstract_inverted_index":{"Recently,":[0],"a":[1,31,49,55,68,80,94],"conventional":[2,148],"neural":[3],"decoder":[4,52,73],"for":[5,34],"speech":[6,39,63,100,149],"codec":[7],"has":[8],"shown":[9],"promising":[10],"performance.":[11],"However,":[12],"it":[13,127],"typically":[14],"requires":[15],"some":[16],"prior":[17,69],"knowledge":[18],"of":[19,38,76,105,139],"decoding":[20],"such":[21],"as":[22],"bit":[23],"allocation":[24],"or":[25],"dequantization":[26,81,107],"scheme,":[27],"which":[28,58],"is":[29,128],"not":[30],"universal":[32],"solution":[33],"many":[35],"different":[36],"kinds":[37],"codecs.":[40,150],"In":[41],"order":[42],"to":[43,83,97,146],"address":[44],"this":[45],"limitation,":[46],"we":[47],"propose":[48],"neurally":[50],"optimized":[51],"based":[53],"on":[54,102],"generative":[56,95],"model":[57,82,96,133],"can":[59],"directly":[60],"reconstruct":[61],"the":[62,65,90,99,103,106,131,140,147],"from":[64,89],"bitstream":[66,91],"without":[67],"knowledge.":[70],"The":[71],"proposed":[72,132],"mainly":[74],"consists":[75],"two":[77],"components:":[78],"1)":[79],"group":[84],"and":[85,92,121,142],"dequantize":[86],"related":[87],"bits":[88],"2)":[93],"restore":[98],"conditioned":[101],"output":[104],"model.":[108],"Through":[109],"experiments":[110],"with":[111],"mixed":[112],"excitation":[113,119],"linear":[114],"prediction":[115],"(MELP),":[116],"Advanced":[117],"multi-band":[118],"(AMBE),":[120],"SPEEX":[122],"at":[123],"around":[124],"2.4":[125],"kb/s,":[126],"showed":[129,134],"that":[130],"better":[135],"performance":[136],"in":[137],"most":[138],"objective":[141],"subjective":[143],"evaluation":[144],"compared":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}