{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KTRX56IMPTTSRHR2O7ERTXSVUP","short_pith_number":"pith:KTRX56IM","schema_version":"1.0","canonical_sha256":"54e37ef90c7ce7289e3a77c919de55a3f7d7b30d05b067c3ea9952dfdc7dfb61","source":{"kind":"arxiv","id":"2310.07246","version":2},"attestation_state":"computed","paper":{"title":"Vec-Tok Speech: speech vectorization and tokenization for neural speech generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heng Lu, Hongbin Zhou, Lei Xie, Tao Li, Wendi He, Xinfa Zhu, Yi Lei, Yuanjun Lv","submitted_at":"2023-10-11T07:23:27Z","abstract_excerpt":"Language models (LMs) have recently flourished in natural language processing and computer vision, generating high-fidelity texts or images in various tasks. In contrast, the current speech generative models are still struggling regarding speech quality and task generalization. This paper presents Vec-Tok Speech, an extensible framework that resembles multiple speech generation tasks, generating expressive and high-fidelity speech. Specifically, we propose a novel speech codec based on speech vectors and semantic tokens. Speech vectors contain acoustic details contributing to high-fidelity spe"},"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":"2310.07246","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-10-11T07:23:27Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"594c302f269b4704177b547b80b5215f383c6c701762b255911bd39b4d1cd06f","abstract_canon_sha256":"26e63f46c9a7e6f9461fbc2c48b53444baa7129d0d3df2dc914b4722ec6f045b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:55.235262Z","signature_b64":"rIsNXThXQ9QJ+CHQUQg7CccqdI3hgUx6MKXJSTa6O6HjTLV6kgdn6lIq5XH8PVkE+ks8nJ8IGS29ItA6IK7fDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54e37ef90c7ce7289e3a77c919de55a3f7d7b30d05b067c3ea9952dfdc7dfb61","last_reissued_at":"2026-07-05T06:59:55.234659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:55.234659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vec-Tok Speech: speech vectorization and tokenization for neural speech generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heng Lu, Hongbin Zhou, Lei Xie, Tao Li, Wendi He, Xinfa Zhu, Yi Lei, Yuanjun Lv","submitted_at":"2023-10-11T07:23:27Z","abstract_excerpt":"Language models (LMs) have recently flourished in natural language processing and computer vision, generating high-fidelity texts or images in various tasks. In contrast, the current speech generative models are still struggling regarding speech quality and task generalization. This paper presents Vec-Tok Speech, an extensible framework that resembles multiple speech generation tasks, generating expressive and high-fidelity speech. Specifically, we propose a novel speech codec based on speech vectors and semantic tokens. Speech vectors contain acoustic details contributing to high-fidelity spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07246","kind":"arxiv","version":2},"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/2310.07246/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":"2310.07246","created_at":"2026-07-05T06:59:55.234740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07246v2","created_at":"2026-07-05T06:59:55.234740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07246","created_at":"2026-07-05T06:59:55.234740+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTRX56IMPTTS","created_at":"2026-07-05T06:59:55.234740+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTRX56IMPTTSRHR2","created_at":"2026-07-05T06:59:55.234740+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTRX56IM","created_at":"2026-07-05T06:59:55.234740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02062","citing_title":"LMPAN: A Lightweight Multi-Path Alignment Network for Joint Full-Duplex Acoustic Echo Cancellation and Noise Suppression","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTRX56IMPTTSRHR2O7ERTXSVUP","json":"https://pith.science/pith/KTRX56IMPTTSRHR2O7ERTXSVUP.json","graph_json":"https://pith.science/api/pith-number/KTRX56IMPTTSRHR2O7ERTXSVUP/graph.json","events_json":"https://pith.science/api/pith-number/KTRX56IMPTTSRHR2O7ERTXSVUP/events.json","paper":"https://pith.science/paper/KTRX56IM"},"agent_actions":{"view_html":"https://pith.science/pith/KTRX56IMPTTSRHR2O7ERTXSVUP","download_json":"https://pith.science/pith/KTRX56IMPTTSRHR2O7ERTXSVUP.json","view_paper":"https://pith.science/paper/KTRX56IM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07246&json=true","fetch_graph":"https://pith.science/api/pith-number/KTRX56IMPTTSRHR2O7ERTXSVUP/graph.json","fetch_events":"https://pith.science/api/pith-number/KTRX56IMPTTSRHR2O7ERTXSVUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTRX56IMPTTSRHR2O7ERTXSVUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTRX56IMPTTSRHR2O7ERTXSVUP/action/storage_attestation","attest_author":"https://pith.science/pith/KTRX56IMPTTSRHR2O7ERTXSVUP/action/author_attestation","sign_citation":"https://pith.science/pith/KTRX56IMPTTSRHR2O7ERTXSVUP/action/citation_signature","submit_replication":"https://pith.science/pith/KTRX56IMPTTSRHR2O7ERTXSVUP/action/replication_record"}},"created_at":"2026-07-05T06:59:55.234740+00:00","updated_at":"2026-07-05T06:59:55.234740+00:00"}