{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DCH7B4YDGOTE2K6PR5HWPB4PGW","short_pith_number":"pith:DCH7B4YD","schema_version":"1.0","canonical_sha256":"188ff0f30333a64d2bcf8f4f67878f35a8786042ddb1b07ca36bef462d88de42","source":{"kind":"arxiv","id":"2606.05892","version":1},"attestation_state":"computed","paper":{"title":"VoCodec: A Low-bitrate Streamable Neural Speech Codec with Voicing-driven Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ji Wu, Li-Rong Dai, Rui-Chen Zheng, Xiao-Hang Jiang, Yang Ai, Zhen-Hua Ling","submitted_at":"2026-06-04T09:00:13Z","abstract_excerpt":"Neural speech codecs are key to speech transmission and storage, but most use uniform quantization across frames, allocating the same bitrate regardless of content and wasting bits. We propose VoCodec, a low-bitrate streamable neural speech codec with voicing-driven quantization that assigns higher bitrate to voiced frames and lower bitrate to unvoiced frames according to perceptual sensitivity. VoCodec embeds a voicing detector in a fully causal encoder-quantizer-decoder neural coding framework, using residual scalar-vector quantization for voiced frames and simple scalar quantization for unv"},"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":"2606.05892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-04T09:00:13Z","cross_cats_sorted":[],"title_canon_sha256":"11733b89c5b2e0bb56c48d25422fbee037b564d877ba1aa77bc9d796aeb1f817","abstract_canon_sha256":"b34ec41e568d911a0890c1ce20d62ea5baf2ca14d593a7efcf1cc283fd61fef5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:07.071264Z","signature_b64":"PT18RhAy42h+7JU42e3qm9DCRw99zq4sQrXM5qU1/q975NaEgmeij53yS6zIFd7GyBvEpv3SP7OXRIznH9shAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"188ff0f30333a64d2bcf8f4f67878f35a8786042ddb1b07ca36bef462d88de42","last_reissued_at":"2026-06-05T01:15:07.070853Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:07.070853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoCodec: A Low-bitrate Streamable Neural Speech Codec with Voicing-driven Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ji Wu, Li-Rong Dai, Rui-Chen Zheng, Xiao-Hang Jiang, Yang Ai, Zhen-Hua Ling","submitted_at":"2026-06-04T09:00:13Z","abstract_excerpt":"Neural speech codecs are key to speech transmission and storage, but most use uniform quantization across frames, allocating the same bitrate regardless of content and wasting bits. We propose VoCodec, a low-bitrate streamable neural speech codec with voicing-driven quantization that assigns higher bitrate to voiced frames and lower bitrate to unvoiced frames according to perceptual sensitivity. VoCodec embeds a voicing detector in a fully causal encoder-quantizer-decoder neural coding framework, using residual scalar-vector quantization for voiced frames and simple scalar quantization for unv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05892","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/2606.05892/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":"2606.05892","created_at":"2026-06-05T01:15:07.070918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05892v1","created_at":"2026-06-05T01:15:07.070918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05892","created_at":"2026-06-05T01:15:07.070918+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCH7B4YDGOTE","created_at":"2026-06-05T01:15:07.070918+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCH7B4YDGOTE2K6P","created_at":"2026-06-05T01:15:07.070918+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCH7B4YD","created_at":"2026-06-05T01:15:07.070918+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/DCH7B4YDGOTE2K6PR5HWPB4PGW","json":"https://pith.science/pith/DCH7B4YDGOTE2K6PR5HWPB4PGW.json","graph_json":"https://pith.science/api/pith-number/DCH7B4YDGOTE2K6PR5HWPB4PGW/graph.json","events_json":"https://pith.science/api/pith-number/DCH7B4YDGOTE2K6PR5HWPB4PGW/events.json","paper":"https://pith.science/paper/DCH7B4YD"},"agent_actions":{"view_html":"https://pith.science/pith/DCH7B4YDGOTE2K6PR5HWPB4PGW","download_json":"https://pith.science/pith/DCH7B4YDGOTE2K6PR5HWPB4PGW.json","view_paper":"https://pith.science/paper/DCH7B4YD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05892&json=true","fetch_graph":"https://pith.science/api/pith-number/DCH7B4YDGOTE2K6PR5HWPB4PGW/graph.json","fetch_events":"https://pith.science/api/pith-number/DCH7B4YDGOTE2K6PR5HWPB4PGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCH7B4YDGOTE2K6PR5HWPB4PGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCH7B4YDGOTE2K6PR5HWPB4PGW/action/storage_attestation","attest_author":"https://pith.science/pith/DCH7B4YDGOTE2K6PR5HWPB4PGW/action/author_attestation","sign_citation":"https://pith.science/pith/DCH7B4YDGOTE2K6PR5HWPB4PGW/action/citation_signature","submit_replication":"https://pith.science/pith/DCH7B4YDGOTE2K6PR5HWPB4PGW/action/replication_record"}},"created_at":"2026-06-05T01:15:07.070918+00:00","updated_at":"2026-06-05T01:15:07.070918+00:00"}