{"id":"https://openalex.org/W4405709688","doi":"https://doi.org/10.1109/iscslp63861.2024.10800135","title":"A Differential Quantization Based End-to-End Neural Speech Codec","display_name":"A Differential Quantization Based End-to-End Neural Speech Codec","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709688","doi":"https://doi.org/10.1109/iscslp63861.2024.10800135"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5051131928","display_name":"Pingli Lu","orcid":"https://orcid.org/0000-0002-2980-4454"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pincheng Lu","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology,Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040488464","display_name":"Liang Xu","orcid":"https://orcid.org/0000-0002-4952-7300"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Xu","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology,Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378323","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0001-6063-9808"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology,Beijing"],"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology,Beijing","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051131928"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21965877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9463000297546387,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9463000297546387,"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/T10860","display_name":"Speech and Audio Processing","score":0.9269999861717224,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7431701421737671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7015267610549927},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6502659916877747},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.587692379951477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5790485143661499},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4374357759952545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2922290563583374},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16579917073249817},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.14703556895256042}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7431701421737671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015267610549927},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6502659916877747},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.587692379951477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5790485143661499},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4374357759952545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2922290563583374},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16579917073249817},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.14703556895256042}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1481955708","https://openalex.org/W1849277567","https://openalex.org/W2064675550","https://openalex.org/W2097645910","https://openalex.org/W2124509324","https://openalex.org/W2151626637","https://openalex.org/W2752796333","https://openalex.org/W2963242190","https://openalex.org/W3180355996","https://openalex.org/W3198533616","https://openalex.org/W3215615641","https://openalex.org/W4307323391","https://openalex.org/W4375869380","https://openalex.org/W4385245566","https://openalex.org/W4392902628","https://openalex.org/W6636170946","https://openalex.org/W6639363673","https://openalex.org/W6782293762","https://openalex.org/W6783867762","https://openalex.org/W6852581948"],"related_works":["https://openalex.org/W2129913000","https://openalex.org/W2374470469","https://openalex.org/W1911859126","https://openalex.org/W2352448339","https://openalex.org/W4404782863","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W3095556352","https://openalex.org/W2159899134","https://openalex.org/W2363660481"],"abstract_inverted_index":{"Speech":[0],"codecs":[1,23,38,52,67],"efficiently":[2],"compress":[3],"speech":[4,22,37,42,51,88,123,142],"signals,":[5],"reducing":[6],"the":[7,13,47,56,94,98,121],"bandwidth":[8],"occupied":[9],"during":[10],"communication.":[11],"With":[12],"development":[14],"of":[15,49,100,140],"neural":[16,26,36,50,87],"networks":[17],"and":[18,103,127,158],"deep":[19],"learning,":[20],"end-to-end":[21],"based":[24,69,86],"on":[25,70,97],"network":[27],"structures":[28],"have":[29],"emerged.":[30],"Compared":[31],"to":[32,60,118],"traditional":[33],"codecs,":[34],"these":[35,66],"can":[39,135],"reconstruct":[40],"higher-quality":[41],"at":[43,77,143,148],"lower":[44],"bitrates.":[45,79],"However,":[46],"performance":[48,76],"drastically":[53],"deteriorates":[54],"when":[55],"communication":[57],"bitrate":[58],"drops":[59],"1":[61],"kbps":[62,145],"or":[63],"below,":[64],"as":[65,108,111],"are":[68],"residual":[71],"quantization,":[72],"which":[73],"has":[74],"limited":[75],"low":[78],"In":[80,92],"this":[81],"paper,":[82],"a":[83,116,137],"differential":[84],"quantization":[85,95],"codec":[89],"is":[90,154],"proposed.":[91],"particular,":[93],"focuses":[96],"importance":[99],"difference":[101],"frames":[102],"preserves":[104],"key":[105],"information":[106],"with":[107],"few":[109],"bits":[110],"possible.":[112],"Meanwhile,":[113],"we":[114],"propose":[115],"compensator":[117],"further":[119],"improve":[120],"reconstructed":[122,141],"quality.":[124],"Both":[125],"subjective":[126],"objective":[128],"evaluations":[129],"demonstrate":[130],"that":[131],"our":[132],"proposed":[133],"method":[134],"achieve":[136],"higher":[138],"quality":[139],"0.6":[144],"than":[146],"Sound-Stream":[147],"3":[149],"kbps.":[150],"The":[151],"entire":[152],"model":[153],"causal,":[155],"supporting":[156],"streaming":[157],"real-time":[159],"inference.":[160]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}