{"id":"https://openalex.org/W4408352880","doi":"https://doi.org/10.1109/icassp49660.2025.10889508","title":"Variable Bitrate Residual Vector Quantization for Audio Coding","display_name":"Variable Bitrate Residual Vector Quantization for Audio Coding","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352880","doi":"https://doi.org/10.1109/icassp49660.2025.10889508"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5013284291","display_name":"Yunkee Chae","orcid":"https://orcid.org/0009-0000-8073-3754"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yunkee Chae","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027289427","display_name":"Woosung Choi","orcid":"https://orcid.org/0000-0002-7001-3099"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Woosung Choi","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028881036","display_name":"Yuhta Takida","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhta Takida","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031164776","display_name":"Junghyun Koo","orcid":"https://orcid.org/0009-0004-4468-0367"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junghyun Koo","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087321595","display_name":"Yukara Ikemiya","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukara Ikemiya","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040961663","display_name":"Zhi Zhong","orcid":"https://orcid.org/0000-0002-8730-5530"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Zhong","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069612434","display_name":"Kin Wai Cheuk","orcid":"https://orcid.org/0000-0003-3213-8242"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kin Wai Cheuk","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017282176","display_name":"Marco A. Mart\u00ednez-Ram\u00edrez","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco A. Mart\u00ednez-Ram\u00edrez","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081140658","display_name":"Kyogu Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyogu Lee","raw_affiliation_strings":["IPAI"],"affiliations":[{"raw_affiliation_string":"IPAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103537853","display_name":"Wei\u2010Hsiang Liao","orcid":"https://orcid.org/0000-0003-4113-1894"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Hsiang Liao","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony AI"],"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5013284291"],"corresponding_institution_ids":["https://openalex.org/I2800278093"],"apc_list":null,"apc_paid":null,"fwci":2.8193,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89171021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9986000061035156,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9822999835014343,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.9815999865531921,"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/vector-quantization","display_name":"Vector quantization","score":0.7183530926704407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6328423023223877},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5948126316070557},{"id":"https://openalex.org/keywords/variable-bitrate","display_name":"Variable bitrate","score":0.5889041423797607},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5879396200180054},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5026178359985352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4968602955341339},{"id":"https://openalex.org/keywords/transform-coding","display_name":"Transform coding","score":0.481777161359787},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4457356929779053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3168543875217438},{"id":"https://openalex.org/keywords/bit-rate","display_name":"Bit rate","score":0.2781918942928314},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.2511582672595978},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23951223492622375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2313646376132965},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1443440318107605},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.1239883303642273}],"concepts":[{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.7183530926704407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328423023223877},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5948126316070557},{"id":"https://openalex.org/C57667952","wikidata":"https://www.wikidata.org/wiki/Q1154443","display_name":"Variable bitrate","level":3,"score":0.5889041423797607},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5879396200180054},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5026178359985352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4968602955341339},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.481777161359787},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4457356929779053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3168543875217438},{"id":"https://openalex.org/C2987812609","wikidata":"https://www.wikidata.org/wiki/Q194158","display_name":"Bit rate","level":2,"score":0.2781918942928314},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.2511582672595978},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23951223492622375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2313646376132965},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1443440318107605},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.1239883303642273},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317106","display_name":"Sony","ror":"https://ror.org/04wzv3n59"},{"id":"https://openalex.org/F4320321292","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1670669358","https://openalex.org/W2086381917","https://openalex.org/W2124509324","https://openalex.org/W2593116425","https://openalex.org/W2604392022","https://openalex.org/W2962891349","https://openalex.org/W2964058413","https://openalex.org/W2998572311","https://openalex.org/W3014578089","https://openalex.org/W3037038648","https://openalex.org/W3159481202","https://openalex.org/W3215615641","https://openalex.org/W4225905067","https://openalex.org/W4307323391","https://openalex.org/W4372342907","https://openalex.org/W6674330103","https://openalex.org/W6695676441","https://openalex.org/W6763945542","https://openalex.org/W6766320909","https://openalex.org/W6771467084","https://openalex.org/W6779577414","https://openalex.org/W6791299810","https://openalex.org/W6802517614","https://openalex.org/W6846889673","https://openalex.org/W6853515095"],"related_works":["https://openalex.org/W2115984063","https://openalex.org/W3209251257","https://openalex.org/W2160220319","https://openalex.org/W2138799587","https://openalex.org/W2377001183","https://openalex.org/W2072046374","https://openalex.org/W2167107465","https://openalex.org/W2373451165","https://openalex.org/W2534663775","https://openalex.org/W2106898123"],"abstract_inverted_index":{"Recent":[0],"state-of-the-art":[1,127],"neural":[2],"audio":[3,56],"compression":[4],"models":[5,17],"have":[6],"progressively":[7],"adopted":[8],"residual":[9],"vector":[10],"quantization":[11],"(RVQ).":[12],"Despite":[13],"this":[14,47],"success,":[15],"these":[16],"employ":[18],"a":[19,76,100],"fixed":[20],"number":[21,67],"of":[22,32,68],"codebooks":[23,69],"per":[24,71],"frame,":[25],"which":[26,58],"can":[27],"be":[28],"suboptimal":[29],"in":[30,36],"terms":[31],"rate-distortion":[33],"tradeoff,":[34],"particularly":[35],"scenarios":[37],"with":[38],"simple":[39],"input":[40],"audio,":[41],"such":[42],"as":[43],"silence.":[44],"To":[45],"address":[46],"limitation,":[48],"we":[49,74],"propose":[50,75],"variable":[51],"bitrate":[52],"RVQ":[53],"(VRVQ)":[54],"for":[55,60,80],"codecs,":[57],"allows":[59],"more":[61],"efficient":[62],"coding":[63],"by":[64],"adapting":[65],"the":[66,81,88,92,106,115,125],"used":[70],"frame.":[72],"Furthermore,":[73],"gradient":[77],"estimation":[78],"method":[79,117],"non-differentiable":[82],"masking":[83],"operation":[84],"that":[85,105],"transforms":[86],"from":[87],"importance":[89,94],"map":[90],"to":[91,114,124],"binary":[93],"mask,":[95],"improving":[96],"model":[97],"training":[98,108],"via":[99],"straight-through":[101],"estimator.":[102],"We":[103],"demonstrate":[104],"proposed":[107],"framework":[109],"achieves":[110],"superior":[111],"results":[112],"compared":[113],"baseline":[116],"and":[118],"shows":[119],"further":[120],"improvement":[121],"when":[122],"applied":[123],"current":[126],"codec.":[128],"Audio":[129],"samples":[130],"are":[131],"available":[132],"at:":[133],"https://yoongi43.github.io/VBRRVQ.github.io/":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}
