{"id":"https://openalex.org/W7204968321","doi":"https://doi.org/10.48550/arxiv.2608.31037","title":"Language-Statistical Analysis of Neural Audio Codec Tokens Across Architectures, Corpora, and Noise Conditions","display_name":"Language-Statistical Analysis of Neural Audio Codec Tokens Across Architectures, Corpora, and Noise Conditions","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204968321","doi":"https://doi.org/10.48550/arxiv.2608.31037"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.31037","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31037","pdf_url":"https://arxiv.org/pdf/2608.31037","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.31037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109692719","display_name":"Joonyong Park","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Joonyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847","observed_orcids":["https://orcid.org/0000-0003-0520-7847"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takamichi, Shinnosuke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104260047","display_name":"David M. Chan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chan, David M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011471256","display_name":"Shunsuke Kando","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kando, Shunsuke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613","observed_orcids":["https://orcid.org/0000-0002-7967-2613"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saito, Yuki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617","observed_orcids":["https://orcid.org/0000-0003-0876-5617"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saruwatari, Hiroshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5756999850273132,"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":0.5756999850273132,"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":0.3953000009059906,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.016300000250339508,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/neural-audio-codecs","display_name":"neural audio codecs","score":0.9990000128746033},{"id":"https://openalex.org/keywords/residual-vector-quantization","display_name":"residual vector quantization","score":0.8600000143051147},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"vector quantization","score":0.9229999780654907},{"id":"https://openalex.org/keywords/zipf-s-law","display_name":"Zipf's law","score":0.9269999861717224},{"id":"https://openalex.org/keywords/heaps-law","display_name":"Heaps' law","score":0.9269999861717224},{"id":"https://openalex.org/keywords/jensen-shannon-divergence","display_name":"Jensen-Shannon divergence","score":0.9929999709129333},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.7620000243186951},{"id":"https://openalex.org/keywords/mel-cepstral-distortion","display_name":"Mel cepstral distortion","score":0.9259999990463257},{"id":"https://openalex.org/keywords/speech-tokenization","display_name":"speech tokenization","score":0.36800000071525574}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6776000261306763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6488000154495239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6366000175476074},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5062999725341797},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42910000681877136},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4259999990463257},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.29980000853538513},{"id":"https://openalex.org/C112633086","wikidata":"https://www.wikidata.org/wiki/Q381287","display_name":"White noise","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.31037","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31037","pdf_url":"https://arxiv.org/pdf/2608.31037","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,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2608.31037","doi":"https://doi.org/10.48550/arxiv.2608.31037","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.31037","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.31037","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31037","pdf_url":"https://arxiv.org/pdf/2608.31037","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7148281569","https://openalex.org/W4416965928","https://openalex.org/W7125121788","https://openalex.org/W7216068851","https://openalex.org/W4402112168","https://openalex.org/W7081568565","https://openalex.org/W7130409387","https://openalex.org/W7214738485","https://openalex.org/W7222714199","https://openalex.org/W4416855533"],"abstract_inverted_index":{"Neural":[0],"audio":[1],"codecs":[2,137,157],"(NACs)":[3],"convert":[4],"speech":[5],"into":[6],"discrete":[7],"token":[8,26,69],"sequences,":[9],"and":[10,39,49,54,61,75,90,98,129,144,154,161],"prior":[11],"work":[12],"has":[13],"reported":[14,134],"that":[15],"these":[16],"sequences":[17],"follow":[18],"language-like":[19],"statistical":[20],"laws.":[21],"This":[22],"paper":[23],"analyzes":[24],"the":[25,102],"statistics":[27],"of":[28],"13":[29],"NACs":[30],"spanning":[31],"multi-codebook":[32],"residual":[33],"vector":[34],"quantization":[35],"(RVQ),":[36],"single-codebook":[37,155],"VQ,":[38],"non-VQ":[40,152],"designs,":[41],"evaluated":[42],"on":[43],"three":[44],"corpora":[45],"under":[46,124,142],"clean,":[47],"white-noise,":[48],"real-world":[50],"DEMAND-noise":[51],"conditions.":[52],"Zipf":[53],"Heaps":[55],"parameters,":[56],"unigram":[57,99,115],"entropy,":[58],"codebook":[59],"occupancy,":[60],"Jensen-Shannon":[62],"divergence":[63],"(JSD)":[64],"are":[65],"estimated":[66],"from":[67],"matched":[68],"samples":[70],"with":[71,107,119],"explicit":[72],"fit-validity":[73],"safeguards":[74],"family-conditional":[76],"$n$-gram":[77],"orders.":[78],"Corpus":[79],"identity":[80],"explains":[81],"little":[82],"variance":[83],"in":[84,94,139,151,159],"any":[85],"metric,":[86],"whereas":[87],"acoustic":[88],"condition":[89],"quantizer":[91],"meta-category":[92],"dominate":[93],"a":[95,113],"metric-dependent":[96],"way,":[97],"entropy":[100],"is":[101,117],"metric":[103],"most":[104,122],"strongly":[105],"associated":[106,118],"meta-category.":[108],"Clean-to-noise":[109],"JSD":[110],"computed":[111],"at":[112],"common":[114],"order":[116],"mel-cepstral":[120],"distortion":[121],"clearly":[123],"DEMAND":[125,145],"noise.":[126],"The":[127],"collapse":[128],"explosion":[130,148],"degradation":[131],"signatures":[132],"previously":[133],"for":[135,172],"RVQ":[136,140],"concentrate":[138],"cells":[141],"white":[143],"noise,":[146],"respectively;":[147],"also":[149],"occurs":[150],"codecs,":[153],"VQ":[156],"shift":[158],"occupancy":[160],"distribution":[162],"shape":[163],"without":[164],"either":[165],"signature.":[166],"These":[167],"results":[168],"provide":[169],"architecture-conditioned":[170],"conventions":[171],"applying":[173],"language-statistical":[174],"analysis":[175],"to":[176],"NAC":[177],"tokens.":[178]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-02T00:00:00"}