{"id":"https://openalex.org/W3214758449","doi":"https://doi.org/10.1109/taslp.2021.3129353","title":"Scalable and Efficient Neural Speech Coding: A Hybrid Design","display_name":"Scalable and Efficient Neural Speech Coding: A Hybrid Design","publication_year":2021,"publication_date":"2021-11-19","ids":{"openalex":"https://openalex.org/W3214758449","doi":"https://doi.org/10.1109/taslp.2021.3129353","mag":"3214758449"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3129353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3129353","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.14776","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047870570","display_name":"Kai Zhen","orcid":"https://orcid.org/0000-0003-4133-8158"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Zhen","raw_affiliation_strings":["Department of Computer Science and Cognitive Science Program, Indiana University, Bloomington, IN, USA"],"raw_orcid":"https://orcid.org/0000-0003-4133-8158","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Cognitive Science Program, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033055249","display_name":"Jongmo Sung","orcid":"https://orcid.org/0000-0002-3396-1137"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongmo Sung","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, Korea"],"raw_orcid":"https://orcid.org/0000-0002-3396-1137","affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005473429","display_name":"Mi Suk Lee","orcid":"https://orcid.org/0000-0001-8951-5032"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mi Suk Lee","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071537541","display_name":"Seungkwon Beack","orcid":"https://orcid.org/0000-0002-6254-2062"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungkwon Beack","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA"],"raw_orcid":"https://orcid.org/0000-0003-3513-8328","affiliations":[{"raw_affiliation_string":"Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3451,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.90401258,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"12","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.795525074005127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6173344254493713},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5325264930725098},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5313031673431396},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5166416764259338},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.49363648891448975},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4630584418773651},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4614293575286865},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3193599581718445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3112031817436218},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.09951478242874146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795525074005127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6173344254493713},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5325264930725098},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5313031673431396},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5166416764259338},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.49363648891448975},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4630584418773651},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4614293575286865},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3193599581718445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3112031817436218},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09951478242874146},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3129353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3129353","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2103.14776","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.14776","pdf_url":"https://arxiv.org/pdf/2103.14776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.14776","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.14776","pdf_url":"https://arxiv.org/pdf/2103.14776","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6299999952316284}],"awards":[{"id":"https://openalex.org/G2891297196","display_name":null,"funder_award_id":"2017-0-00072","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W198453894","https://openalex.org/W1481955708","https://openalex.org/W1490826069","https://openalex.org/W1491878173","https://openalex.org/W1519698338","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1959608418","https://openalex.org/W1963884863","https://openalex.org/W1969526148","https://openalex.org/W1971243715","https://openalex.org/W1994152191","https://openalex.org/W1995562189","https://openalex.org/W2020883660","https://openalex.org/W2044893557","https://openalex.org/W2058075673","https://openalex.org/W2088912280","https://openalex.org/W2109189270","https://openalex.org/W2143612262","https://openalex.org/W2151626637","https://openalex.org/W2151825755","https://openalex.org/W2165291881","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2519091744","https://openalex.org/W2531409750","https://openalex.org/W2585720638","https://openalex.org/W2726515241","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2891355459","https://openalex.org/W2892365986","https://openalex.org/W2897371647","https://openalex.org/W2935711438","https://openalex.org/W2950237361","https://openalex.org/W2952218014","https://openalex.org/W2963091184","https://openalex.org/W2963182577","https://openalex.org/W2963799213","https://openalex.org/W2963840672","https://openalex.org/W2963970792","https://openalex.org/W2964073500","https://openalex.org/W2964121744","https://openalex.org/W2964164354","https://openalex.org/W2964307104","https://openalex.org/W2972354707","https://openalex.org/W2972519044","https://openalex.org/W3015268401","https://openalex.org/W3095248373","https://openalex.org/W3096468295","https://openalex.org/W3099330747","https://openalex.org/W3100270690","https://openalex.org/W3110277971","https://openalex.org/W3125709657","https://openalex.org/W3127686677","https://openalex.org/W6607999887","https://openalex.org/W6629304513","https://openalex.org/W6630442970","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6696085341","https://openalex.org/W6731370813","https://openalex.org/W6741057705","https://openalex.org/W6748409065","https://openalex.org/W6760712927"],"related_works":["https://openalex.org/W2964213236","https://openalex.org/W2126742497","https://openalex.org/W2129913000","https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W3095556352","https://openalex.org/W2159899134","https://openalex.org/W2363660481"],"abstract_inverted_index":{"We":[0,13,69],"present":[1],"a":[2,24,34,53,94,103,176,246],"scalable":[3,95],"and":[4,31,49,60,84,169,263,271],"efficient":[5],"neural":[6,26,35,241],"waveform":[7,36],"coding":[8,17,51,58,115,129,157,252],"system":[9,181,190,255,276],"for":[10,151],"speech":[11,16,231,242,251],"compression.":[12],"formulate":[14],"the":[15,57,66,89,113,180,213,219],"problem":[18],"as":[19,33,52,80,149,160,175,225,227,245],"an":[20,183],"autoencoding":[21,121],"task,":[22],"where":[23,123],"convolutional":[25],"network":[27],"(CNN)":[28],"performs":[29,127],"encoding":[30],"decoding":[32,220],"codec":[37],"(NWC)":[38],"during":[39,65],"its":[40,136,161],"feedforward":[41],"routine.":[42],"The":[43,164,186,274],"proposed":[44,90,189,275],"NWC":[45,120,125,170,195],"also":[46],"defines":[47],"quantization":[48,174],"entropy":[50],"trainable":[54],"module,":[55],"so":[56],"artifacts":[59],"bitrate":[61,203,215],"control":[62],"are":[63,92],"handled":[64],"optimization":[67],"process.":[68],"achieve":[70,284],"efficiency":[71],"by":[72,171],"introducing":[73],"compact":[74],"model":[75],"components":[76],"to":[77,101,117,130,145,201,206,261,280,283],"NWC,":[78],"such":[79,244],"gated":[81],"residual":[82,98,114,128],"networks":[83],"depthwise":[85],"separable":[86],"convolution.":[87],"Furthermore,":[88],"models":[91],"with":[93,192],"architecture,":[96],"cross-module":[97],"learning":[99],"(CMRL),":[100],"cover":[102,146],"wide":[104],"range":[105],"of":[106,188,229,239],"bitrates.":[107,273],"To":[108],"this":[109],"end,":[110],"we":[111],"employ":[112],"concept":[116],"concatenate":[118],"multiple":[119],"modules,":[122],"each":[124],"module":[126,159],"restore":[131],"any":[132],"reconstruction":[133],"loss":[134],"that":[135,228,238],"preceding":[137],"modules":[138],"have":[139],"created.":[140],"CMRL":[141],"can":[142,277],"scale":[143,278],"down":[144],"lower":[147],"bitrates":[148,282],"well,":[150],"which":[152],"it":[153,233],"employs":[154],"linear":[155],"predictive":[156],"(LPC)":[158],"first":[162],"autoencoder.":[163],"hybrid":[165],"design":[166],"integrates":[167],"LPC":[168],"redefining":[172],"LPC\u2019s":[173],"differentiable":[177],"process,":[178],"making":[179],"training":[182],"end-to-end":[184],"manner.":[185],"decoder":[187],"is":[191,222,234],"either":[193],"one":[194],"(0.12":[196],"million":[197],"parameters)":[198],"in":[199,212],"low":[200,226,270],"medium":[202,272],"ranges":[204],"(12":[205],"20":[207],"kbps)":[208],"or":[209,258],"two":[210],"NWCs":[211],"high":[214],"(32":[216],"kbps).":[217],"Although":[218],"complexity":[221],"not":[223],"yet":[224],"conventional":[230],"codecs,":[232],"significantly":[235],"reduced":[236],"from":[237],"other":[240],"coders,":[243],"WaveNet-based":[247],"vocoder.":[248],"For":[249],"wide-band":[250],"quality,":[253],"our":[254],"yields":[256],"comparable":[257],"superior":[259],"performance":[260],"AMR-WB":[262],"Opus":[264],"on":[265],"TIMIT":[266],"test":[267],"utterances":[268],"at":[269],"up":[279],"higher":[281],"near":[285],"transparent":[286],"performance.":[287]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}