{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GYQ33UGCMFRJCSQNDQKYFXV76J","short_pith_number":"pith:GYQ33UGC","schema_version":"1.0","canonical_sha256":"3621bdd0c26162914a0d1c1582debff2777c58b7324b0461ce9d9c90e7926e3a","source":{"kind":"arxiv","id":"2306.06546","version":2},"attestation_state":"computed","paper":{"title":"High-Fidelity Audio Compression with Improved RVQGAN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alejandro Luebs, Ishaan Kumar, Kundan Kumar, Prem Seetharaman, Rithesh Kumar","submitted_at":"2023-06-11T00:13:00Z","abstract_excerpt":"Language models have been successfully used to model natural signals, such as images, speech, and music. A key component of these models is a high quality neural compression model that can compress high-dimensional natural signals into lower dimensional discrete tokens. To that end, we introduce a high-fidelity universal neural audio compression algorithm that achieves ~90x compression of 44.1 KHz audio into tokens at just 8kbps bandwidth. We achieve this by combining advances in high-fidelity audio generation with better vector quantization techniques from the image domain, along with improve"},"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":"2306.06546","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-11T00:13:00Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"02c8d4d00e7b3005937eeae9321dd1b51932d4e29bb0908cf2b6741715e5af29","abstract_canon_sha256":"ddec06fd0d697a07447d9ba85a69bfb4662795009a47d14ef131a5468752d08c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:44.478732Z","signature_b64":"0/TfVk8DUQzoARLu/gCj6PXG0OlpHkcKLH9mvFq8hKo0BVaq6EiQVO7+9hMaYaqipRyvmA1et0kW32qQrl6TAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3621bdd0c26162914a0d1c1582debff2777c58b7324b0461ce9d9c90e7926e3a","last_reissued_at":"2026-07-05T07:05:44.478247Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:44.478247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Fidelity Audio Compression with Improved RVQGAN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alejandro Luebs, Ishaan Kumar, Kundan Kumar, Prem Seetharaman, Rithesh Kumar","submitted_at":"2023-06-11T00:13:00Z","abstract_excerpt":"Language models have been successfully used to model natural signals, such as images, speech, and music. A key component of these models is a high quality neural compression model that can compress high-dimensional natural signals into lower dimensional discrete tokens. To that end, we introduce a high-fidelity universal neural audio compression algorithm that achieves ~90x compression of 44.1 KHz audio into tokens at just 8kbps bandwidth. We achieve this by combining advances in high-fidelity audio generation with better vector quantization techniques from the image domain, along with improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06546","kind":"arxiv","version":2},"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/2306.06546/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":"2306.06546","created_at":"2026-07-05T07:05:44.478295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06546v2","created_at":"2026-07-05T07:05:44.478295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06546","created_at":"2026-07-05T07:05:44.478295+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYQ33UGCMFRJ","created_at":"2026-07-05T07:05:44.478295+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYQ33UGCMFRJCSQN","created_at":"2026-07-05T07:05:44.478295+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYQ33UGC","created_at":"2026-07-05T07:05:44.478295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21372","citing_title":"NAC: Neural Action Codec for Vision-Language-Action Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10046","citing_title":"Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27627","citing_title":"HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01537","citing_title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20519","citing_title":"Codec-Robust Attacks on Audio LLMs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01929","citing_title":"Woosh: A Sound Effects Foundation Model","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10281","citing_title":"Drum Synthesis from Expressive Drum Grids via Neural Audio Codecs","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYQ33UGCMFRJCSQNDQKYFXV76J","json":"https://pith.science/pith/GYQ33UGCMFRJCSQNDQKYFXV76J.json","graph_json":"https://pith.science/api/pith-number/GYQ33UGCMFRJCSQNDQKYFXV76J/graph.json","events_json":"https://pith.science/api/pith-number/GYQ33UGCMFRJCSQNDQKYFXV76J/events.json","paper":"https://pith.science/paper/GYQ33UGC"},"agent_actions":{"view_html":"https://pith.science/pith/GYQ33UGCMFRJCSQNDQKYFXV76J","download_json":"https://pith.science/pith/GYQ33UGCMFRJCSQNDQKYFXV76J.json","view_paper":"https://pith.science/paper/GYQ33UGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06546&json=true","fetch_graph":"https://pith.science/api/pith-number/GYQ33UGCMFRJCSQNDQKYFXV76J/graph.json","fetch_events":"https://pith.science/api/pith-number/GYQ33UGCMFRJCSQNDQKYFXV76J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYQ33UGCMFRJCSQNDQKYFXV76J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYQ33UGCMFRJCSQNDQKYFXV76J/action/storage_attestation","attest_author":"https://pith.science/pith/GYQ33UGCMFRJCSQNDQKYFXV76J/action/author_attestation","sign_citation":"https://pith.science/pith/GYQ33UGCMFRJCSQNDQKYFXV76J/action/citation_signature","submit_replication":"https://pith.science/pith/GYQ33UGCMFRJCSQNDQKYFXV76J/action/replication_record"}},"created_at":"2026-07-05T07:05:44.478295+00:00","updated_at":"2026-07-05T07:05:44.478295+00:00"}