{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:INOS44GTCOAMGFR5YYAM2S7LEI","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":"54506cc78010f579b08be4607b59ce6751f2cd6b86bcb06042e71da9bc649a31","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-11T16:22:57Z","title_canon_sha256":"adf43b8a5d5fcca3dba0922703a3bd9956eba983fb49f5cb7660e4a6261c41d8"},"schema_version":"1.0","source":{"id":"2406.07422","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07422","created_at":"2026-07-05T08:30:23Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07422v1","created_at":"2026-07-05T08:30:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07422","created_at":"2026-07-05T08:30:23Z"},{"alias_kind":"pith_short_12","alias_value":"INOS44GTCOAM","created_at":"2026-07-05T08:30:23Z"},{"alias_kind":"pith_short_16","alias_value":"INOS44GTCOAMGFR5","created_at":"2026-07-05T08:30:23Z"},{"alias_kind":"pith_short_8","alias_value":"INOS44GT","created_at":"2026-07-05T08:30:23Z"}],"graph_snapshots":[{"event_id":"sha256:8984589542c882296c60f30dd9fddcb1553676d3f3e54a4effdf1be62031477e","target":"graph","created_at":"2026-07-05T08:30:23Z","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/2406.07422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The multi-codebook speech codec enables the application of large language models (LLM) in TTS but bottlenecks efficiency and robustness due to multi-sequence prediction. To avoid this obstacle, we propose Single-Codec, a single-codebook single-sequence codec, which employs a disentangled VQ-VAE to decouple speech into a time-invariant embedding and a phonetically-rich discrete sequence. Furthermore, the encoder is enhanced with 1) contextual modeling with a BLSTM module to exploit the temporal information, 2) a hybrid sampling module to alleviate distortion from upsampling and downsampling, an","authors_text":"Hanzhao Li, Haohan Guo, Hao Yin, Lei Xie, Liumeng Xue, Xinfa Zhu, Yuanjun Lv, Yunlin Chen, Zhifei Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-11T16:22:57Z","title":"Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07422","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":"sha256:99ae7b1df0b9cfba2f9be6641873a004dc6e9de1c9e883d4f0723645768404bb","target":"record","created_at":"2026-07-05T08:30:23Z","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":"54506cc78010f579b08be4607b59ce6751f2cd6b86bcb06042e71da9bc649a31","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-11T16:22:57Z","title_canon_sha256":"adf43b8a5d5fcca3dba0922703a3bd9956eba983fb49f5cb7660e4a6261c41d8"},"schema_version":"1.0","source":{"id":"2406.07422","kind":"arxiv","version":1}},"canonical_sha256":"435d2e70d31380c3163dc600cd4beb222ead93408c4e651c5ea9911c8c0d19d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"435d2e70d31380c3163dc600cd4beb222ead93408c4e651c5ea9911c8c0d19d3","first_computed_at":"2026-07-05T08:30:23.383455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:23.383455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kfKMR33veyIratnTMTvTYH7ogPF/l+wj8Lxxzz+lt+XtBnQ8RFXrAGXFq3hcn7PRRGalktEcdYNx8VJiLKzJDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:23.383892Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07422","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99ae7b1df0b9cfba2f9be6641873a004dc6e9de1c9e883d4f0723645768404bb","sha256:8984589542c882296c60f30dd9fddcb1553676d3f3e54a4effdf1be62031477e"],"state_sha256":"e0b2a3a65bcff298e86b2e054946a25eaf8fa98dd5d2ba73ecfa76d7abb63e7c"}