{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:INOS44GTCOAMGFR5YYAM2S7LEI","short_pith_number":"pith:INOS44GT","schema_version":"1.0","canonical_sha256":"435d2e70d31380c3163dc600cd4beb222ead93408c4e651c5ea9911c8c0d19d3","source":{"kind":"arxiv","id":"2406.07422","version":1},"attestation_state":"computed","paper":{"title":"Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hanzhao Li, Haohan Guo, Hao Yin, Lei Xie, Liumeng Xue, Xinfa Zhu, Yuanjun Lv, Yunlin Chen, Zhifei Li","submitted_at":"2024-06-11T16:22:57Z","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"},"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":"2406.07422","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-11T16:22:57Z","cross_cats_sorted":[],"title_canon_sha256":"adf43b8a5d5fcca3dba0922703a3bd9956eba983fb49f5cb7660e4a6261c41d8","abstract_canon_sha256":"54506cc78010f579b08be4607b59ce6751f2cd6b86bcb06042e71da9bc649a31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:23.383892Z","signature_b64":"kfKMR33veyIratnTMTvTYH7ogPF/l+wj8Lxxzz+lt+XtBnQ8RFXrAGXFq3hcn7PRRGalktEcdYNx8VJiLKzJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"435d2e70d31380c3163dc600cd4beb222ead93408c4e651c5ea9911c8c0d19d3","last_reissued_at":"2026-07-05T08:30:23.383455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:23.383455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hanzhao Li, Haohan Guo, Hao Yin, Lei Xie, Liumeng Xue, Xinfa Zhu, Yuanjun Lv, Yunlin Chen, Zhifei Li","submitted_at":"2024-06-11T16:22:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07422","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/2406.07422/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":"2406.07422","created_at":"2026-07-05T08:30:23.383515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07422v1","created_at":"2026-07-05T08:30:23.383515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07422","created_at":"2026-07-05T08:30:23.383515+00:00"},{"alias_kind":"pith_short_12","alias_value":"INOS44GTCOAM","created_at":"2026-07-05T08:30:23.383515+00:00"},{"alias_kind":"pith_short_16","alias_value":"INOS44GTCOAMGFR5","created_at":"2026-07-05T08:30:23.383515+00:00"},{"alias_kind":"pith_short_8","alias_value":"INOS44GT","created_at":"2026-07-05T08:30:23.383515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12940","citing_title":"Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01537","citing_title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2505.24437","citing_title":"SwitchCodec: A High-Fidelity Nerual Audio Codec With Sparse Quantization","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INOS44GTCOAMGFR5YYAM2S7LEI","json":"https://pith.science/pith/INOS44GTCOAMGFR5YYAM2S7LEI.json","graph_json":"https://pith.science/api/pith-number/INOS44GTCOAMGFR5YYAM2S7LEI/graph.json","events_json":"https://pith.science/api/pith-number/INOS44GTCOAMGFR5YYAM2S7LEI/events.json","paper":"https://pith.science/paper/INOS44GT"},"agent_actions":{"view_html":"https://pith.science/pith/INOS44GTCOAMGFR5YYAM2S7LEI","download_json":"https://pith.science/pith/INOS44GTCOAMGFR5YYAM2S7LEI.json","view_paper":"https://pith.science/paper/INOS44GT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07422&json=true","fetch_graph":"https://pith.science/api/pith-number/INOS44GTCOAMGFR5YYAM2S7LEI/graph.json","fetch_events":"https://pith.science/api/pith-number/INOS44GTCOAMGFR5YYAM2S7LEI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INOS44GTCOAMGFR5YYAM2S7LEI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INOS44GTCOAMGFR5YYAM2S7LEI/action/storage_attestation","attest_author":"https://pith.science/pith/INOS44GTCOAMGFR5YYAM2S7LEI/action/author_attestation","sign_citation":"https://pith.science/pith/INOS44GTCOAMGFR5YYAM2S7LEI/action/citation_signature","submit_replication":"https://pith.science/pith/INOS44GTCOAMGFR5YYAM2S7LEI/action/replication_record"}},"created_at":"2026-07-05T08:30:23.383515+00:00","updated_at":"2026-07-05T08:30:23.383515+00:00"}