{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TNW5QXXSXXDCCDHWH5ELXJ62T7","short_pith_number":"pith:TNW5QXXS","canonical_record":{"source":{"id":"2209.10887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-22T09:43:17Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"03d492cead20f18269b8eb15a73ff3f5bc4a824764e9ba32b477846441b1f852","abstract_canon_sha256":"5d19ac9836de6ad1d774a630437a6371ef9e93ac69141187ba9c360b1600da24"},"schema_version":"1.0"},"canonical_sha256":"9b6dd85ef2bdc6210cf63f48bba7da9fea6bd6b52277a9f0910e41b9b195fec6","source":{"kind":"arxiv","id":"2209.10887","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.10887","created_at":"2026-07-05T05:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2209.10887v1","created_at":"2026-07-05T05:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10887","created_at":"2026-07-05T05:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"TNW5QXXSXXDC","created_at":"2026-07-05T05:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"TNW5QXXSXXDCCDHW","created_at":"2026-07-05T05:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"TNW5QXXS","created_at":"2026-07-05T05:00:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TNW5QXXSXXDCCDHWH5ELXJ62T7","target":"record","payload":{"canonical_record":{"source":{"id":"2209.10887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-22T09:43:17Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"03d492cead20f18269b8eb15a73ff3f5bc4a824764e9ba32b477846441b1f852","abstract_canon_sha256":"5d19ac9836de6ad1d774a630437a6371ef9e93ac69141187ba9c360b1600da24"},"schema_version":"1.0"},"canonical_sha256":"9b6dd85ef2bdc6210cf63f48bba7da9fea6bd6b52277a9f0910e41b9b195fec6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:08.360698Z","signature_b64":"TqZnC+gWzIdGrQ8IY6388lEHaxFK69MW204ligBUJWCVASsy5TKWrolW/ZJPElghuUzuaqc8ybp/h8XBM5VaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b6dd85ef2bdc6210cf63f48bba7da9fea6bd6b52277a9f0910e41b9b195fec6","last_reissued_at":"2026-07-05T05:00:08.360342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:08.360342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.10887","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sR+yTiqn8ElrI8toQ2/FN3MLaeNVvn391W0PmQyto+LlErd/eIgza15REK+jrPUMm+YNtAdWlROEoTdIJKAkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:31:25.784273Z"},"content_sha256":"506d5d3a3368c47e1d169bf608e89c743d470176656870a0335fa70cdaca3a46","schema_version":"1.0","event_id":"sha256:506d5d3a3368c47e1d169bf608e89c743d470176656870a0335fa70cdaca3a46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TNW5QXXSXXDCCDHWH5ELXJ62T7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fenglong Xie, Frank K. Soong, Haohan Guo, Helen Meng, Xixin Wu","submitted_at":"2022-09-22T09:43:17Z","abstract_excerpt":"We propose a Multi-Stage, Multi-Codebook (MSMC) approach to high-performance neural TTS synthesis. A vector-quantized, variational autoencoder (VQ-VAE) based feature analyzer is used to encode Mel spectrograms of speech training data by down-sampling progressively in multiple stages into MSMC Representations (MSMCRs) with different time resolutions, and quantizing them with multiple VQ codebooks, respectively. Multi-stage predictors are trained to map the input text sequence to MSMCRs progressively by minimizing a combined loss of the reconstruction Mean Square Error (MSE) and \"triplet loss\". "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10887","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/2209.10887/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:00:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LuR3hagY9XExzN9RT6z2CUYX1mRpO7FY6w0IMaDltCBLqR7aEO7LRCSqDoALhhsXc1CaunbinZXhTQDdZ0eXAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T16:31:25.784790Z"},"content_sha256":"4cce923584753bf72edeb43a614428bf885cda03380b08456983101ec2904bb5","schema_version":"1.0","event_id":"sha256:4cce923584753bf72edeb43a614428bf885cda03380b08456983101ec2904bb5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNW5QXXSXXDCCDHWH5ELXJ62T7/bundle.json","state_url":"https://pith.science/pith/TNW5QXXSXXDCCDHWH5ELXJ62T7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNW5QXXSXXDCCDHWH5ELXJ62T7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T16:31:25Z","links":{"resolver":"https://pith.science/pith/TNW5QXXSXXDCCDHWH5ELXJ62T7","bundle":"https://pith.science/pith/TNW5QXXSXXDCCDHWH5ELXJ62T7/bundle.json","state":"https://pith.science/pith/TNW5QXXSXXDCCDHWH5ELXJ62T7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNW5QXXSXXDCCDHWH5ELXJ62T7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TNW5QXXSXXDCCDHWH5ELXJ62T7","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":"5d19ac9836de6ad1d774a630437a6371ef9e93ac69141187ba9c360b1600da24","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-22T09:43:17Z","title_canon_sha256":"03d492cead20f18269b8eb15a73ff3f5bc4a824764e9ba32b477846441b1f852"},"schema_version":"1.0","source":{"id":"2209.10887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.10887","created_at":"2026-07-05T05:00:08Z"},{"alias_kind":"arxiv_version","alias_value":"2209.10887v1","created_at":"2026-07-05T05:00:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10887","created_at":"2026-07-05T05:00:08Z"},{"alias_kind":"pith_short_12","alias_value":"TNW5QXXSXXDC","created_at":"2026-07-05T05:00:08Z"},{"alias_kind":"pith_short_16","alias_value":"TNW5QXXSXXDCCDHW","created_at":"2026-07-05T05:00:08Z"},{"alias_kind":"pith_short_8","alias_value":"TNW5QXXS","created_at":"2026-07-05T05:00:08Z"}],"graph_snapshots":[{"event_id":"sha256:4cce923584753bf72edeb43a614428bf885cda03380b08456983101ec2904bb5","target":"graph","created_at":"2026-07-05T05:00:08Z","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/2209.10887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a Multi-Stage, Multi-Codebook (MSMC) approach to high-performance neural TTS synthesis. A vector-quantized, variational autoencoder (VQ-VAE) based feature analyzer is used to encode Mel spectrograms of speech training data by down-sampling progressively in multiple stages into MSMC Representations (MSMCRs) with different time resolutions, and quantizing them with multiple VQ codebooks, respectively. Multi-stage predictors are trained to map the input text sequence to MSMCRs progressively by minimizing a combined loss of the reconstruction Mean Square Error (MSE) and \"triplet loss\". ","authors_text":"Fenglong Xie, Frank K. Soong, Haohan Guo, Helen Meng, Xixin Wu","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-22T09:43:17Z","title":"A Multi-Stage Multi-Codebook VQ-VAE Approach to High-Performance Neural TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10887","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":"sha256:506d5d3a3368c47e1d169bf608e89c743d470176656870a0335fa70cdaca3a46","target":"record","created_at":"2026-07-05T05:00:08Z","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":"5d19ac9836de6ad1d774a630437a6371ef9e93ac69141187ba9c360b1600da24","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-09-22T09:43:17Z","title_canon_sha256":"03d492cead20f18269b8eb15a73ff3f5bc4a824764e9ba32b477846441b1f852"},"schema_version":"1.0","source":{"id":"2209.10887","kind":"arxiv","version":1}},"canonical_sha256":"9b6dd85ef2bdc6210cf63f48bba7da9fea6bd6b52277a9f0910e41b9b195fec6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b6dd85ef2bdc6210cf63f48bba7da9fea6bd6b52277a9f0910e41b9b195fec6","first_computed_at":"2026-07-05T05:00:08.360342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:00:08.360342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TqZnC+gWzIdGrQ8IY6388lEHaxFK69MW204ligBUJWCVASsy5TKWrolW/ZJPElghuUzuaqc8ybp/h8XBM5VaBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:00:08.360698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.10887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:506d5d3a3368c47e1d169bf608e89c743d470176656870a0335fa70cdaca3a46","sha256:4cce923584753bf72edeb43a614428bf885cda03380b08456983101ec2904bb5"],"state_sha256":"d32305d80849f07b35d5b7202033c0e89d68819418e01d437029171200aefa4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NxBha84xQ/NNWbUUFRpqcJMbuyka1+wJJ8GOBFPNMbd1dVhgPiMkfJEmv+dBmfNiShGcvF+ZyRmxBfogCEEqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T16:31:25.789347Z","bundle_sha256":"18fb23edc2a2d60f85bfaab6cb32171783413135e831dad657af6d84cf7c3f3c"}}