{"id":"https://openalex.org/W4408353695","doi":"https://doi.org/10.1109/icassp49660.2025.10890096","title":"Code Drift: Towards Idempotent Neural Audio Codecs","display_name":"Code Drift: Towards Idempotent Neural Audio Codecs","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353695","doi":"https://doi.org/10.1109/icassp49660.2025.10890096"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890096","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":"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/A5075935325","display_name":"Patrick O\u2019Reilly","orcid":"https://orcid.org/0000-0002-6205-2354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick O\u2019Reilly","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023673004","display_name":"Prem Seetharaman","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prem Seetharaman","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028173993","display_name":"Jiaqu Su","orcid":"https://orcid.org/0009-0004-2040-8596"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaqu Su","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102878078","display_name":"Bryan Pardo","orcid":"https://orcid.org/0000-0002-1427-6492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Pardo","raw_affiliation_strings":["Northwestern University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11309","display_name":"Music and Audio Processing","score":0.9905999898910522,"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/T11309","display_name":"Music and Audio Processing","score":0.9905999898910522,"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/T10860","display_name":"Speech and Audio Processing","score":0.9656999707221985,"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/T10320","display_name":"Neural Networks and Applications","score":0.9538000226020813,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6971806287765503},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6458826065063477},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6012078523635864},{"id":"https://openalex.org/keywords/idempotence","display_name":"Idempotence","score":0.5823182463645935},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5220974683761597},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.32029786705970764},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3199259340763092},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.22017666697502136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12698984146118164},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.06365242600440979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6971806287765503},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6458826065063477},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6012078523635864},{"id":"https://openalex.org/C172252984","wikidata":"https://www.wikidata.org/wiki/Q368988","display_name":"Idempotence","level":2,"score":0.5823182463645935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5220974683761597},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.32029786705970764},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3199259340763092},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.22017666697502136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12698984146118164},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.06365242600440979},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890096","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W2040903332","https://openalex.org/W2752796333","https://openalex.org/W2962891349","https://openalex.org/W2964058413","https://openalex.org/W3093249525","https://openalex.org/W3215615641","https://openalex.org/W4307323391","https://openalex.org/W4372260337","https://openalex.org/W4381786045","https://openalex.org/W4385823130","https://openalex.org/W4392903006","https://openalex.org/W4402115964","https://openalex.org/W4402670057","https://openalex.org/W4402672020","https://openalex.org/W4404782459","https://openalex.org/W4406461488","https://openalex.org/W6634241205","https://openalex.org/W6639363673","https://openalex.org/W6757817989","https://openalex.org/W6761551260","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6788158735","https://openalex.org/W6802036239","https://openalex.org/W6802838302","https://openalex.org/W6838843145","https://openalex.org/W6840815571","https://openalex.org/W6845479124","https://openalex.org/W6852490468","https://openalex.org/W6853096648","https://openalex.org/W6853188576","https://openalex.org/W6853515095","https://openalex.org/W6854494257","https://openalex.org/W6855885476","https://openalex.org/W6860885380","https://openalex.org/W6861548716","https://openalex.org/W6862144568","https://openalex.org/W6868809805","https://openalex.org/W6869097082","https://openalex.org/W6869755106","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2964213236","https://openalex.org/W2163719598","https://openalex.org/W3161919736","https://openalex.org/W2387018512","https://openalex.org/W1594270709","https://openalex.org/W2107680156","https://openalex.org/W4301184752","https://openalex.org/W2288771647","https://openalex.org/W2751422192","https://openalex.org/W1509797384"],"abstract_inverted_index":{"Neural":[0],"codecs":[1,21,68,140],"have":[2,22,44],"demonstrated":[3],"strong":[4],"performance":[5,132],"in":[6,36],"high-fidelity":[7],"compression":[8,37,144],"of":[9,55,61,72,90,110,138],"audio":[10,77],"signals":[11],"at":[12],"low":[13,91],"bitrates.":[14],"The":[15],"token-based":[16],"representations":[17],"produced":[18],"by":[19],"these":[20],"proven":[23],"particularly":[24],"useful":[25],"for":[26,97,141],"generative":[27,116,147],"modeling.":[28],"While":[29],"much":[30],"research":[31],"has":[32],"focused":[33],"on":[34,112],"improvements":[35],"ratio":[38],"and":[39,93,119,145],"perceptual":[40],"transparency,":[41],"recent":[42],"works":[43],"largely":[45],"overlooked":[46],"another":[47],"desirable":[48],"codec":[49,103],"property":[50],"\u2013":[51,133],"idempotence,":[52,73],"the":[53,108,136],"stability":[54],"compressed":[56],"outputs":[57,78],"under":[58],"multiple":[59],"rounds":[60],"encoding.":[62],"We":[63,86,105],"find":[64,120],"that":[65,121],"state-of-the-art":[66],"neural":[67,139],"exhibit":[69],"varied":[70],"degrees":[71],"with":[74],"some":[75],"degrading":[76],"significantly":[79],"after":[80],"as":[81,83],"few":[82],"three":[84],"encodings.":[85],"investigate":[87],"possible":[88],"causes":[89],"idempotence":[92,99,111,123],"devise":[94],"a":[95,102,113],"method":[96],"improving":[98],"through":[100],"fine-tuning":[101],"model.":[104],"then":[106],"examine":[107],"effect":[109],"simple":[114],"conditional":[115],"modeling":[117,131,148],"task,":[118],"increased":[122],"can":[124],"be":[125],"achieved":[126],"without":[127],"negatively":[128],"impacting":[129],"downstream":[130],"potentially":[134],"extending":[135],"usefulness":[137],"practical":[142],"file":[143],"iterative":[146],"workflows.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-03-13T00:00:00"}