{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FCZTB7D6CLX7UIKQXSI556T4CA","short_pith_number":"pith:FCZTB7D6","schema_version":"1.0","canonical_sha256":"28b330fc7e12effa2150bc91defa7c1011805e89289c51507dcbfbb501262090","source":{"kind":"arxiv","id":"2509.02244","version":1},"attestation_state":"computed","paper":{"title":"Spectrogram Patch Codec: A 2D Block-Quantized VQ-VAE and HiFi-GAN for Neural Speech Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Luis Felipe Chary, Miguel Arjona Ramirez","submitted_at":"2025-09-02T12:14:41Z","abstract_excerpt":"We present a neural speech codec that challenges the need for complex residual vector quantization (RVQ) stacks by introducing a simpler, single-stage quantization approach. Our method operates directly on the mel-spectrogram, treating it as a 2D data and quantizing non-overlapping 4x4 patches into a single, shared codebook. This patchwise design simplifies the architecture, enables low-latency streaming, and yields a discrete latent grid. To ensure high-fidelity synthesis, we employ a late-stage adversarial fine-tuning for the VQ-VAE and train a HiFi-GAN vocoder from scratch on the codec's re"},"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":"2509.02244","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-09-02T12:14:41Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"f110adb23e5ad8ae6107f903537e139457abd9259eb3777bd53f9149e0ae0fb8","abstract_canon_sha256":"ef80cb93f3c954f57a1cb5a013371a9592aa3ce31f1b9e1d323f93441411dcc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:34.647422Z","signature_b64":"KT+11eejNOvFkCcUHHRQhQlO+h3UQfNTeV78Mj3K11qVu09dyoLl98oXVsWQZwVYHFxKqge+5QdQ0V8rPuSTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28b330fc7e12effa2150bc91defa7c1011805e89289c51507dcbfbb501262090","last_reissued_at":"2026-07-05T12:03:34.647069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:34.647069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectrogram Patch Codec: A 2D Block-Quantized VQ-VAE and HiFi-GAN for Neural Speech Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Luis Felipe Chary, Miguel Arjona Ramirez","submitted_at":"2025-09-02T12:14:41Z","abstract_excerpt":"We present a neural speech codec that challenges the need for complex residual vector quantization (RVQ) stacks by introducing a simpler, single-stage quantization approach. Our method operates directly on the mel-spectrogram, treating it as a 2D data and quantizing non-overlapping 4x4 patches into a single, shared codebook. This patchwise design simplifies the architecture, enables low-latency streaming, and yields a discrete latent grid. To ensure high-fidelity synthesis, we employ a late-stage adversarial fine-tuning for the VQ-VAE and train a HiFi-GAN vocoder from scratch on the codec's re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02244","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/2509.02244/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":"2509.02244","created_at":"2026-07-05T12:03:34.647122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02244v1","created_at":"2026-07-05T12:03:34.647122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02244","created_at":"2026-07-05T12:03:34.647122+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCZTB7D6CLX7","created_at":"2026-07-05T12:03:34.647122+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCZTB7D6CLX7UIKQ","created_at":"2026-07-05T12:03:34.647122+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCZTB7D6","created_at":"2026-07-05T12:03:34.647122+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/FCZTB7D6CLX7UIKQXSI556T4CA","json":"https://pith.science/pith/FCZTB7D6CLX7UIKQXSI556T4CA.json","graph_json":"https://pith.science/api/pith-number/FCZTB7D6CLX7UIKQXSI556T4CA/graph.json","events_json":"https://pith.science/api/pith-number/FCZTB7D6CLX7UIKQXSI556T4CA/events.json","paper":"https://pith.science/paper/FCZTB7D6"},"agent_actions":{"view_html":"https://pith.science/pith/FCZTB7D6CLX7UIKQXSI556T4CA","download_json":"https://pith.science/pith/FCZTB7D6CLX7UIKQXSI556T4CA.json","view_paper":"https://pith.science/paper/FCZTB7D6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02244&json=true","fetch_graph":"https://pith.science/api/pith-number/FCZTB7D6CLX7UIKQXSI556T4CA/graph.json","fetch_events":"https://pith.science/api/pith-number/FCZTB7D6CLX7UIKQXSI556T4CA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCZTB7D6CLX7UIKQXSI556T4CA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCZTB7D6CLX7UIKQXSI556T4CA/action/storage_attestation","attest_author":"https://pith.science/pith/FCZTB7D6CLX7UIKQXSI556T4CA/action/author_attestation","sign_citation":"https://pith.science/pith/FCZTB7D6CLX7UIKQXSI556T4CA/action/citation_signature","submit_replication":"https://pith.science/pith/FCZTB7D6CLX7UIKQXSI556T4CA/action/replication_record"}},"created_at":"2026-07-05T12:03:34.647122+00:00","updated_at":"2026-07-05T12:03:34.647122+00:00"}