{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PFCDVVMVXBIQ5NDUE4DIRNDJH3","short_pith_number":"pith:PFCDVVMV","schema_version":"1.0","canonical_sha256":"79443ad595b8510eb474270688b4693efb62cdb2668e1ac6ae9badcb563ea1fa","source":{"kind":"arxiv","id":"2404.19441","version":3},"attestation_state":"computed","paper":{"title":"ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Enmao Diao, Yuzhe Gu","submitted_at":"2024-04-30T10:44:33Z","abstract_excerpt":"Neural speech codecs aim to compress input signals into minimal bits while maintaining content quality in a low-latency manner. However, existing neural codecs often trade model complexity for reconstruction performance. These codecs primarily use convolutional blocks for feature transformation, which are not inherently suited for capturing the local redundancies in speech signals. To compensate, they require either adversarial discriminators or a large number of model parameters to enhance audio quality. In response to these challenges, we introduce the Efficient Speech Codec (ESC), a lightwe"},"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":"2404.19441","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-30T10:44:33Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"97a0fe34e32eb42629c9a0634ea15e26b8a0ab62fbdd6a338dcf24c2baeaf6e2","abstract_canon_sha256":"4fb04ed21c0def13a79595f7ca14211db7e2b299762ecfe179397c750e69eab4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:10.184295Z","signature_b64":"T1Lnu0n8Xi/rKzSk7/fcDpIcOGd8CCwfS9yITFyFgVqFTAf0ousOgODuwVVepViDozH6JQGTWuI1/0NOR6WNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79443ad595b8510eb474270688b4693efb62cdb2668e1ac6ae9badcb563ea1fa","last_reissued_at":"2026-07-05T09:15:10.183888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:10.183888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Enmao Diao, Yuzhe Gu","submitted_at":"2024-04-30T10:44:33Z","abstract_excerpt":"Neural speech codecs aim to compress input signals into minimal bits while maintaining content quality in a low-latency manner. However, existing neural codecs often trade model complexity for reconstruction performance. These codecs primarily use convolutional blocks for feature transformation, which are not inherently suited for capturing the local redundancies in speech signals. To compensate, they require either adversarial discriminators or a large number of model parameters to enhance audio quality. In response to these challenges, we introduce the Efficient Speech Codec (ESC), a lightwe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19441","kind":"arxiv","version":3},"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/2404.19441/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":"2404.19441","created_at":"2026-07-05T09:15:10.183942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.19441v3","created_at":"2026-07-05T09:15:10.183942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19441","created_at":"2026-07-05T09:15:10.183942+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFCDVVMVXBIQ","created_at":"2026-07-05T09:15:10.183942+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFCDVVMVXBIQ5NDU","created_at":"2026-07-05T09:15:10.183942+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFCDVVMV","created_at":"2026-07-05T09:15:10.183942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11631","citing_title":"Benchmarking Neural Speech Compression from a Rate-Distortion Perspective","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFCDVVMVXBIQ5NDUE4DIRNDJH3","json":"https://pith.science/pith/PFCDVVMVXBIQ5NDUE4DIRNDJH3.json","graph_json":"https://pith.science/api/pith-number/PFCDVVMVXBIQ5NDUE4DIRNDJH3/graph.json","events_json":"https://pith.science/api/pith-number/PFCDVVMVXBIQ5NDUE4DIRNDJH3/events.json","paper":"https://pith.science/paper/PFCDVVMV"},"agent_actions":{"view_html":"https://pith.science/pith/PFCDVVMVXBIQ5NDUE4DIRNDJH3","download_json":"https://pith.science/pith/PFCDVVMVXBIQ5NDUE4DIRNDJH3.json","view_paper":"https://pith.science/paper/PFCDVVMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.19441&json=true","fetch_graph":"https://pith.science/api/pith-number/PFCDVVMVXBIQ5NDUE4DIRNDJH3/graph.json","fetch_events":"https://pith.science/api/pith-number/PFCDVVMVXBIQ5NDUE4DIRNDJH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFCDVVMVXBIQ5NDUE4DIRNDJH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFCDVVMVXBIQ5NDUE4DIRNDJH3/action/storage_attestation","attest_author":"https://pith.science/pith/PFCDVVMVXBIQ5NDUE4DIRNDJH3/action/author_attestation","sign_citation":"https://pith.science/pith/PFCDVVMVXBIQ5NDUE4DIRNDJH3/action/citation_signature","submit_replication":"https://pith.science/pith/PFCDVVMVXBIQ5NDUE4DIRNDJH3/action/replication_record"}},"created_at":"2026-07-05T09:15:10.183942+00:00","updated_at":"2026-07-05T09:15:10.183942+00:00"}