{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CDJJK27C6ELI52QJKE4DKEFERF","short_pith_number":"pith:CDJJK27C","schema_version":"1.0","canonical_sha256":"10d2956be2f1168eea0951383510a4896d6b3815ea040aeb6943171b94e73e42","source":{"kind":"arxiv","id":"2504.08470","version":1},"attestation_state":"computed","paper":{"title":"On the Design of Diffusion-based Neural Speech Codecs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Brendel, Pietro Foti","submitted_at":"2025-04-11T11:58:38Z","abstract_excerpt":"Recently, neural speech codecs (NSCs) trained as generative models have shown superior performance compared to conventional codecs at low bitrates. Although most state-of-the-art NSCs are trained as Generative Adversarial Networks (GANs), Diffusion Models (DMs), a recent class of generative models, represent a promising alternative due to their superior performance in image generation relative to GANs. Consequently, DMs have been successfully applied for audio and speech coding among various other audio generation applications. However, the design of diffusion-based NSCs has not yet been explo"},"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":"2504.08470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-11T11:58:38Z","cross_cats_sorted":["cs.AI","cs.MM","eess.AS"],"title_canon_sha256":"51f9e34ad2d5158de6640d39d3e6eb20b3a1e8c19c7748b8a0fede6303cbc187","abstract_canon_sha256":"f1f86cd5f4af1f4610ba89f437840a9735e3947f839c5f64c04ef6f26a57dbcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:49.673980Z","signature_b64":"2sCtFoqcgF3VAmGyEAApH63TWPjBTxXQLJOzYxJHL1rFEi5rfTp2KOVSmoDh8A7VUJagBi8iMtfx4RPnSai5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10d2956be2f1168eea0951383510a4896d6b3815ea040aeb6943171b94e73e42","last_reissued_at":"2026-07-05T10:47:49.673493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:49.673493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Design of Diffusion-based Neural Speech Codecs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Brendel, Pietro Foti","submitted_at":"2025-04-11T11:58:38Z","abstract_excerpt":"Recently, neural speech codecs (NSCs) trained as generative models have shown superior performance compared to conventional codecs at low bitrates. Although most state-of-the-art NSCs are trained as Generative Adversarial Networks (GANs), Diffusion Models (DMs), a recent class of generative models, represent a promising alternative due to their superior performance in image generation relative to GANs. Consequently, DMs have been successfully applied for audio and speech coding among various other audio generation applications. However, the design of diffusion-based NSCs has not yet been explo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08470","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/2504.08470/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":"2504.08470","created_at":"2026-07-05T10:47:49.673552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08470v1","created_at":"2026-07-05T10:47:49.673552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08470","created_at":"2026-07-05T10:47:49.673552+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDJJK27C6ELI","created_at":"2026-07-05T10:47:49.673552+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDJJK27C6ELI52QJ","created_at":"2026-07-05T10:47:49.673552+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDJJK27C","created_at":"2026-07-05T10:47:49.673552+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/CDJJK27C6ELI52QJKE4DKEFERF","json":"https://pith.science/pith/CDJJK27C6ELI52QJKE4DKEFERF.json","graph_json":"https://pith.science/api/pith-number/CDJJK27C6ELI52QJKE4DKEFERF/graph.json","events_json":"https://pith.science/api/pith-number/CDJJK27C6ELI52QJKE4DKEFERF/events.json","paper":"https://pith.science/paper/CDJJK27C"},"agent_actions":{"view_html":"https://pith.science/pith/CDJJK27C6ELI52QJKE4DKEFERF","download_json":"https://pith.science/pith/CDJJK27C6ELI52QJKE4DKEFERF.json","view_paper":"https://pith.science/paper/CDJJK27C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08470&json=true","fetch_graph":"https://pith.science/api/pith-number/CDJJK27C6ELI52QJKE4DKEFERF/graph.json","fetch_events":"https://pith.science/api/pith-number/CDJJK27C6ELI52QJKE4DKEFERF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDJJK27C6ELI52QJKE4DKEFERF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDJJK27C6ELI52QJKE4DKEFERF/action/storage_attestation","attest_author":"https://pith.science/pith/CDJJK27C6ELI52QJKE4DKEFERF/action/author_attestation","sign_citation":"https://pith.science/pith/CDJJK27C6ELI52QJKE4DKEFERF/action/citation_signature","submit_replication":"https://pith.science/pith/CDJJK27C6ELI52QJKE4DKEFERF/action/replication_record"}},"created_at":"2026-07-05T10:47:49.673552+00:00","updated_at":"2026-07-05T10:47:49.673552+00:00"}