{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2M6XYWIRZNLERKHAVRIOA22XNA","short_pith_number":"pith:2M6XYWIR","schema_version":"1.0","canonical_sha256":"d33d7c5911cb5648a8e0ac50e06b57680a9f2428e962e58e1a8b0f4c94b7c0ce","source":{"kind":"arxiv","id":"2412.01053","version":3},"attestation_state":"computed","paper":{"title":"FreeCodec: A disentangled neural speech codec with fewer tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jie Chen, Li Xiao, Long Ma, Weiping tu, Yike Zhang, Youqiang Zheng, Yueteng Kang, Yuhong Yang","submitted_at":"2024-12-02T02:29:22Z","abstract_excerpt":"Neural speech codecs have gained great attention for their outstanding reconstruction with discrete token representations.\n  It is a crucial component in generative tasks such as speech coding and large language models (LLM).\n  However, most works based on residual vector quantization perform worse with fewer tokens due to low coding efficiency for modeling complex coupled information.\n  In this paper, we propose a neural speech codec named FreeCodec which employs a more effective encoding framework by decomposing intrinsic properties of speech into different components:\n  1) a global vector i"},"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":"2412.01053","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-02T02:29:22Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ae93cc5441efc9634fd377daf38f576e61f58d707cf7555618a5d2408aef1850","abstract_canon_sha256":"4cad3d809c52a87b1c016734cc4cca28fd14f2bf873ed2fd6710a1482a446d59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:32.654571Z","signature_b64":"HY149by+Qz7kmATSp8EPo7ju/uCCNGC0J+ypzLVTHzVNBhLdyvy1FWMaK3K/HpfwruW7dUErckK7m8TzDrPbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d33d7c5911cb5648a8e0ac50e06b57680a9f2428e962e58e1a8b0f4c94b7c0ce","last_reissued_at":"2026-07-05T11:28:32.654057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:32.654057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeCodec: A disentangled neural speech codec with fewer tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jie Chen, Li Xiao, Long Ma, Weiping tu, Yike Zhang, Youqiang Zheng, Yueteng Kang, Yuhong Yang","submitted_at":"2024-12-02T02:29:22Z","abstract_excerpt":"Neural speech codecs have gained great attention for their outstanding reconstruction with discrete token representations.\n  It is a crucial component in generative tasks such as speech coding and large language models (LLM).\n  However, most works based on residual vector quantization perform worse with fewer tokens due to low coding efficiency for modeling complex coupled information.\n  In this paper, we propose a neural speech codec named FreeCodec which employs a more effective encoding framework by decomposing intrinsic properties of speech into different components:\n  1) a global vector i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01053","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/2412.01053/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":"2412.01053","created_at":"2026-07-05T11:28:32.654118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01053v3","created_at":"2026-07-05T11:28:32.654118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01053","created_at":"2026-07-05T11:28:32.654118+00:00"},{"alias_kind":"pith_short_12","alias_value":"2M6XYWIRZNLE","created_at":"2026-07-05T11:28:32.654118+00:00"},{"alias_kind":"pith_short_16","alias_value":"2M6XYWIRZNLERKHA","created_at":"2026-07-05T11:28:32.654118+00:00"},{"alias_kind":"pith_short_8","alias_value":"2M6XYWIR","created_at":"2026-07-05T11:28:32.654118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12940","citing_title":"Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment","ref_index":84,"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":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2M6XYWIRZNLERKHAVRIOA22XNA","json":"https://pith.science/pith/2M6XYWIRZNLERKHAVRIOA22XNA.json","graph_json":"https://pith.science/api/pith-number/2M6XYWIRZNLERKHAVRIOA22XNA/graph.json","events_json":"https://pith.science/api/pith-number/2M6XYWIRZNLERKHAVRIOA22XNA/events.json","paper":"https://pith.science/paper/2M6XYWIR"},"agent_actions":{"view_html":"https://pith.science/pith/2M6XYWIRZNLERKHAVRIOA22XNA","download_json":"https://pith.science/pith/2M6XYWIRZNLERKHAVRIOA22XNA.json","view_paper":"https://pith.science/paper/2M6XYWIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01053&json=true","fetch_graph":"https://pith.science/api/pith-number/2M6XYWIRZNLERKHAVRIOA22XNA/graph.json","fetch_events":"https://pith.science/api/pith-number/2M6XYWIRZNLERKHAVRIOA22XNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2M6XYWIRZNLERKHAVRIOA22XNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2M6XYWIRZNLERKHAVRIOA22XNA/action/storage_attestation","attest_author":"https://pith.science/pith/2M6XYWIRZNLERKHAVRIOA22XNA/action/author_attestation","sign_citation":"https://pith.science/pith/2M6XYWIRZNLERKHAVRIOA22XNA/action/citation_signature","submit_replication":"https://pith.science/pith/2M6XYWIRZNLERKHAVRIOA22XNA/action/replication_record"}},"created_at":"2026-07-05T11:28:32.654118+00:00","updated_at":"2026-07-05T11:28:32.654118+00:00"}