{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6UAEGV7Y4LVI7BCDSMLEXNLLUV","short_pith_number":"pith:6UAEGV7Y","schema_version":"1.0","canonical_sha256":"f5004357f8e2ea8f844393164bb56ba5673ce3c3a47963a48d1575d360aceaf8","source":{"kind":"arxiv","id":"2509.01390","version":1},"attestation_state":"computed","paper":{"title":"Analysing the Language of Neural Audio Codecs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"David M. Chan, Hiroshi Saruwatari, Joonyong Park, Shinnosuke Takamichi, Shunsuke Kando, Yuki Saito","submitted_at":"2025-09-01T11:36:33Z","abstract_excerpt":"This study presents a comparative analysis of the statistical and linguistic properties of neural audio codecs (NACs). We investigate discrete speech tokens produced by various NAC models, examining their adherence to linguistic statistical laws such as Zipf's law and Heaps' law, as well as their entropy and redundancy. To assess how these token-level properties relate to semantic and acoustic preservation in synthesized speech, we evaluate intelligibility using error rates of automatic speech recognition, and quality using the UTMOS score. Our results reveal that NAC tokens, particularly 3-gr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.01390","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-01T11:36:33Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"61fac3a5b6c2d38f37efc95d121ddc10bbaa65e8bb80becde7b0374fc8101055","abstract_canon_sha256":"36572d99d8ebb6f18dae6813a5614fd56737f132596747b49470c37bdc53be79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:59.692692Z","signature_b64":"XJRuXGVTnOowpmsHm78fePWQcuYYs85G36+tHVjPlg1jxejm79eNp/u+dQ5qdVLJCDYyJiCUpgeJkczBUpfSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5004357f8e2ea8f844393164bb56ba5673ce3c3a47963a48d1575d360aceaf8","last_reissued_at":"2026-07-05T12:02:59.692137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:59.692137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysing the Language of Neural Audio Codecs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"David M. Chan, Hiroshi Saruwatari, Joonyong Park, Shinnosuke Takamichi, Shunsuke Kando, Yuki Saito","submitted_at":"2025-09-01T11:36:33Z","abstract_excerpt":"This study presents a comparative analysis of the statistical and linguistic properties of neural audio codecs (NACs). We investigate discrete speech tokens produced by various NAC models, examining their adherence to linguistic statistical laws such as Zipf's law and Heaps' law, as well as their entropy and redundancy. To assess how these token-level properties relate to semantic and acoustic preservation in synthesized speech, we evaluate intelligibility using error rates of automatic speech recognition, and quality using the UTMOS score. Our results reveal that NAC tokens, particularly 3-gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01390","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2509.01390/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.01390","created_at":"2026-07-05T12:02:59.692204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01390v1","created_at":"2026-07-05T12:02:59.692204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01390","created_at":"2026-07-05T12:02:59.692204+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UAEGV7Y4LVI","created_at":"2026-07-05T12:02:59.692204+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UAEGV7Y4LVI7BCD","created_at":"2026-07-05T12:02:59.692204+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UAEGV7Y","created_at":"2026-07-05T12:02:59.692204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6UAEGV7Y4LVI7BCDSMLEXNLLUV","json":"https://pith.science/pith/6UAEGV7Y4LVI7BCDSMLEXNLLUV.json","graph_json":"https://pith.science/api/pith-number/6UAEGV7Y4LVI7BCDSMLEXNLLUV/graph.json","events_json":"https://pith.science/api/pith-number/6UAEGV7Y4LVI7BCDSMLEXNLLUV/events.json","paper":"https://pith.science/paper/6UAEGV7Y"},"agent_actions":{"view_html":"https://pith.science/pith/6UAEGV7Y4LVI7BCDSMLEXNLLUV","download_json":"https://pith.science/pith/6UAEGV7Y4LVI7BCDSMLEXNLLUV.json","view_paper":"https://pith.science/paper/6UAEGV7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01390&json=true","fetch_graph":"https://pith.science/api/pith-number/6UAEGV7Y4LVI7BCDSMLEXNLLUV/graph.json","fetch_events":"https://pith.science/api/pith-number/6UAEGV7Y4LVI7BCDSMLEXNLLUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UAEGV7Y4LVI7BCDSMLEXNLLUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UAEGV7Y4LVI7BCDSMLEXNLLUV/action/storage_attestation","attest_author":"https://pith.science/pith/6UAEGV7Y4LVI7BCDSMLEXNLLUV/action/author_attestation","sign_citation":"https://pith.science/pith/6UAEGV7Y4LVI7BCDSMLEXNLLUV/action/citation_signature","submit_replication":"https://pith.science/pith/6UAEGV7Y4LVI7BCDSMLEXNLLUV/action/replication_record"}},"created_at":"2026-07-05T12:02:59.692204+00:00","updated_at":"2026-07-05T12:02:59.692204+00:00"}