{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6VTIUCBFLNHXFIYX2XZ74G5E3B","short_pith_number":"pith:6VTIUCBF","schema_version":"1.0","canonical_sha256":"f5668a08255b4f72a317d5f3fe1ba4d862f046e85d88a4527b5f7213113234e3","source":{"kind":"arxiv","id":"2409.12717","version":1},"attestation_state":"computed","paper":{"title":"NDVQ: Robust Neural Audio Codec with Normal Distribution-Based Vector Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Long Zhou, Sanyuan Chen, Shujie Liu, Xie Chen, Zhikang Niu, Ziyang Ma","submitted_at":"2024-09-19T12:41:30Z","abstract_excerpt":"Built upon vector quantization (VQ), discrete audio codec models have achieved great success in audio compression and auto-regressive audio generation. However, existing models face substantial challenges in perceptual quality and signal distortion, especially when operating in extremely low bandwidth, rooted in the sensitivity of the VQ codebook to noise. This degradation poses significant challenges for several downstream tasks, such as codec-based speech synthesis. To address this issue, we propose a novel VQ method, Normal Distribution-based Vector Quantization (NDVQ), by introducing an ex"},"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":"2409.12717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-19T12:41:30Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"64276d16a15f5ce30933e5c2e689d362cb61d9bb6c080ca206bca2776aaf8c60","abstract_canon_sha256":"df92e006f1acec65b620bb6f8367c7d97c241a22313626db34a55f1446c0f8e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:11.201096Z","signature_b64":"jB3k9Qpk+iMS+rwgX/Ol9KT8hedyiqdr/Nbdl6lRqgpiMDZTYTt+lj8ZHlgdV7fmvQIEPo7IjRDDhSw4A56qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5668a08255b4f72a317d5f3fe1ba4d862f046e85d88a4527b5f7213113234e3","last_reissued_at":"2026-07-05T09:09:11.200586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:11.200586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NDVQ: Robust Neural Audio Codec with Normal Distribution-Based Vector Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Long Zhou, Sanyuan Chen, Shujie Liu, Xie Chen, Zhikang Niu, Ziyang Ma","submitted_at":"2024-09-19T12:41:30Z","abstract_excerpt":"Built upon vector quantization (VQ), discrete audio codec models have achieved great success in audio compression and auto-regressive audio generation. However, existing models face substantial challenges in perceptual quality and signal distortion, especially when operating in extremely low bandwidth, rooted in the sensitivity of the VQ codebook to noise. This degradation poses significant challenges for several downstream tasks, such as codec-based speech synthesis. To address this issue, we propose a novel VQ method, Normal Distribution-based Vector Quantization (NDVQ), by introducing an ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12717","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/2409.12717/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":"2409.12717","created_at":"2026-07-05T09:09:11.200651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12717v1","created_at":"2026-07-05T09:09:11.200651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12717","created_at":"2026-07-05T09:09:11.200651+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VTIUCBFLNHX","created_at":"2026-07-05T09:09:11.200651+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VTIUCBFLNHXFIYX","created_at":"2026-07-05T09:09:11.200651+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VTIUCBF","created_at":"2026-07-05T09:09:11.200651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":127,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6VTIUCBFLNHXFIYX2XZ74G5E3B","json":"https://pith.science/pith/6VTIUCBFLNHXFIYX2XZ74G5E3B.json","graph_json":"https://pith.science/api/pith-number/6VTIUCBFLNHXFIYX2XZ74G5E3B/graph.json","events_json":"https://pith.science/api/pith-number/6VTIUCBFLNHXFIYX2XZ74G5E3B/events.json","paper":"https://pith.science/paper/6VTIUCBF"},"agent_actions":{"view_html":"https://pith.science/pith/6VTIUCBFLNHXFIYX2XZ74G5E3B","download_json":"https://pith.science/pith/6VTIUCBFLNHXFIYX2XZ74G5E3B.json","view_paper":"https://pith.science/paper/6VTIUCBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12717&json=true","fetch_graph":"https://pith.science/api/pith-number/6VTIUCBFLNHXFIYX2XZ74G5E3B/graph.json","fetch_events":"https://pith.science/api/pith-number/6VTIUCBFLNHXFIYX2XZ74G5E3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VTIUCBFLNHXFIYX2XZ74G5E3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VTIUCBFLNHXFIYX2XZ74G5E3B/action/storage_attestation","attest_author":"https://pith.science/pith/6VTIUCBFLNHXFIYX2XZ74G5E3B/action/author_attestation","sign_citation":"https://pith.science/pith/6VTIUCBFLNHXFIYX2XZ74G5E3B/action/citation_signature","submit_replication":"https://pith.science/pith/6VTIUCBFLNHXFIYX2XZ74G5E3B/action/replication_record"}},"created_at":"2026-07-05T09:09:11.200651+00:00","updated_at":"2026-07-05T09:09:11.200651+00:00"}