{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W7I6JLO4JCZPGJFGKF5PIURHNI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aded0e7244f687f7a1a256c709655b1a7b4eef1207047fe70c87216f2a6540fe","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-02T04:13:20Z","title_canon_sha256":"6f36e0c64e2d21de3ac9912c51a36809e29d530e6149fe19aedbd702872e4a06"},"schema_version":"1.0","source":{"id":"2409.00933","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00933","created_at":"2026-07-05T09:01:55Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00933v1","created_at":"2026-07-05T09:01:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00933","created_at":"2026-07-05T09:01:55Z"},{"alias_kind":"pith_short_12","alias_value":"W7I6JLO4JCZP","created_at":"2026-07-05T09:01:55Z"},{"alias_kind":"pith_short_16","alias_value":"W7I6JLO4JCZPGJFG","created_at":"2026-07-05T09:01:55Z"},{"alias_kind":"pith_short_8","alias_value":"W7I6JLO4","created_at":"2026-07-05T09:01:55Z"}],"graph_snapshots":[{"event_id":"sha256:ba9dafe4792caa91155cf6b0b52df87cb414239f38aec88ee0629a2cc88d8d49","target":"graph","created_at":"2026-07-05T09:01:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.00933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The long speech sequence has been troubling language models (LM) based TTS approaches in terms of modeling complexity and efficiency. This work proposes SoCodec, a semantic-ordered multi-stream speech codec, to address this issue. It compresses speech into a shorter, multi-stream discrete semantic sequence with multiple tokens at each frame. Meanwhile, the ordered product quantization is proposed to constrain this sequence into an ordered representation. It can be applied with a multi-stream delayed LM to achieve better autoregressive generation along both time and stream axes in TTS. The expe","authors_text":"Dake Guo, Dongchao Yang, Fenglong Xie, Haohan Guo, Helen Meng, Kun Xie, Xixin Wu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-02T04:13:20Z","title":"SoCodec: A Semantic-Ordered Multi-Stream Speech Codec for Efficient Language Model Based Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00933","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:de22adca0625d1d3db9e3aad8b802e79ae09346af8501dfeb0c2a0f1fc4b252a","target":"record","created_at":"2026-07-05T09:01:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aded0e7244f687f7a1a256c709655b1a7b4eef1207047fe70c87216f2a6540fe","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-02T04:13:20Z","title_canon_sha256":"6f36e0c64e2d21de3ac9912c51a36809e29d530e6149fe19aedbd702872e4a06"},"schema_version":"1.0","source":{"id":"2409.00933","kind":"arxiv","version":1}},"canonical_sha256":"b7d1e4addc48b2f324a6517af452276a088baff2e8e4a9ce394935aec28d278d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7d1e4addc48b2f324a6517af452276a088baff2e8e4a9ce394935aec28d278d","first_computed_at":"2026-07-05T09:01:55.462812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:55.462812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wHU5D1RRuF10XDz2H9+ZYwvFSNK28OKqo+VxPRlUpD2mKaI5oEG8X4r3+HlpSvaZRckFZhZqqKP9QBjYYM18Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:55.463286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00933","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de22adca0625d1d3db9e3aad8b802e79ae09346af8501dfeb0c2a0f1fc4b252a","sha256:ba9dafe4792caa91155cf6b0b52df87cb414239f38aec88ee0629a2cc88d8d49"],"state_sha256":"43098371441ada1e16a01c9966e5e793ef8bc15a8cd53e74939b6c71999014b4"}