{"id":"https://openalex.org/W3015268401","doi":"https://doi.org/10.1109/icassp40776.2020.9054347","title":"Efficient and Scalable Neural Residual Waveform Coding with Collaborative Quantization","display_name":"Efficient and Scalable Neural Residual Waveform Coding with Collaborative Quantization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015268401","doi":"https://doi.org/10.1109/icassp40776.2020.9054347","mag":"3015268401"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/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":["Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"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, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"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, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South 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, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South 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":["Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN","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":2.6291,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91210614,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9965000152587891,"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/codebook","display_name":"Codebook","score":0.7794733047485352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.774552583694458},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7025485634803772},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6722651124000549},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6462003588676453},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6345335841178894},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6135429739952087},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5564812421798706},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5305692553520203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4858786463737488},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.42835739254951477},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4227387309074402},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4194347560405731},{"id":"https://openalex.org/keywords/code-excited-linear-prediction","display_name":"Code-excited linear prediction","score":0.4188501238822937},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3971453905105591},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35406482219696045},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25969231128692627},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.2503335475921631},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.12147971987724304},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09925571084022522},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07763311266899109}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7794733047485352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.774552583694458},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7025485634803772},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6722651124000549},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6462003588676453},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6345335841178894},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6135429739952087},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5564812421798706},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5305692553520203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4858786463737488},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.42835739254951477},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4227387309074402},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4194347560405731},{"id":"https://openalex.org/C105964291","wikidata":"https://www.wikidata.org/wiki/Q856184","display_name":"Code-excited linear prediction","level":4,"score":0.4188501238822937},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3971453905105591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35406482219696045},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25969231128692627},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.2503335475921631},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.12147971987724304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09925571084022522},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07763311266899109},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W198453894","https://openalex.org/W1519698338","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1553834069","https://openalex.org/W1653357422","https://openalex.org/W2020883660","https://openalex.org/W2055815603","https://openalex.org/W2103934944","https://openalex.org/W2125126590","https://openalex.org/W2138675764","https://openalex.org/W2148371116","https://openalex.org/W2149288684","https://openalex.org/W2165291881","https://openalex.org/W2194775991","https://openalex.org/W2292235217","https://openalex.org/W2519091744","https://openalex.org/W2606703671","https://openalex.org/W2732044853","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2935711438","https://openalex.org/W2950237361","https://openalex.org/W2963091184","https://openalex.org/W2963182577","https://openalex.org/W2963799213","https://openalex.org/W2964121744","https://openalex.org/W2964164354","https://openalex.org/W2964307104","https://openalex.org/W2972354707","https://openalex.org/W2972519044","https://openalex.org/W4297752165","https://openalex.org/W4298580827","https://openalex.org/W6607999887","https://openalex.org/W6630442970","https://openalex.org/W6631190155","https://openalex.org/W6633114069","https://openalex.org/W6696768431","https://openalex.org/W6741057705","https://openalex.org/W6748409065","https://openalex.org/W6760712927"],"related_works":["https://openalex.org/W2614570504","https://openalex.org/W4236018629","https://openalex.org/W2132539013","https://openalex.org/W3943236","https://openalex.org/W1499374905","https://openalex.org/W2014919663","https://openalex.org/W1593486778","https://openalex.org/W1570840316","https://openalex.org/W2110375858","https://openalex.org/W1586537451"],"abstract_inverted_index":{"Scalability":[0],"and":[1,36,60,64,108],"efficiency":[2],"are":[3,117],"desired":[4],"in":[5,70],"neural":[6,48,57,112],"speech":[7],"codecs,":[8],"which":[9],"supports":[10],"a":[11,23,47,111],"wide":[12],"range":[13],"of":[14,33,55],"bitrates":[15],"for":[16],"applications":[17],"on":[18],"various":[19],"devices.":[20],"We":[21,74,93],"propose":[22],"collaborative":[24],"quantization":[25],"(CQ)":[26],"scheme":[27],"to":[28,46,101],"jointly":[29],"learn":[30],"the":[31,37,52],"codebook":[32],"LPC":[34,45],"coefficients":[35],"corresponding":[38],"residuals.":[39],"CQ":[40,77,97,115],"does":[41],"not":[42],"simply":[43],"shoehorn":[44],"network,":[49],"but":[50],"bridges":[51],"computational":[53],"capacity":[54],"advanced":[56],"network":[58],"models":[59,116],"traditional,":[61],"yet":[62],"efficient":[63],"domain-specific":[65],"digital":[66],"signal":[67],"processing":[68],"methods":[69],"an":[71],"integrated":[72],"manner.":[73],"demonstrate":[75],"that":[76,96],"achieves":[78],"much":[79],"higher":[80],"quality":[81],"than":[82,120,126],"its":[83],"predecessor":[84],"at":[85],"9":[86],"kbps":[87,103],"with":[88,118],"even":[89],"lower":[90],"model":[91],"complexity.":[92],"also":[94],"show":[95],"can":[98],"scale":[99],"up":[100],"24":[102],"where":[104],"it":[105],"outperforms":[106],"AMR-WB":[107],"Opus.":[109],"As":[110],"waveform":[113],"codec,":[114],"less":[119,125],"1":[121],"million":[122],"parameters,":[123],"significantly":[124],"many":[127],"other":[128],"generative":[129],"models.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}