{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Y75EN5IYDJZS3KJSGXHJABMEDK","short_pith_number":"pith:Y75EN5IY","canonical_record":{"source":{"id":"2204.03238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-04-07T06:09:47Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"2c5fdd04807c759d8cc2a6aec3ce4d3c31450990fb662f1c72e199edb8bc5e79","abstract_canon_sha256":"7f797850c10fc8e7b7f836350df04667c23f0c22caf924d9a132232b0eb86df2"},"schema_version":"1.0"},"canonical_sha256":"c7fa46f5181a732da93235ce9005841ab1f6b7591e755c81138a342af4213d1b","source":{"kind":"arxiv","id":"2204.03238","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03238","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03238v1","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03238","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"Y75EN5IYDJZS","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"Y75EN5IYDJZS3KJS","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"Y75EN5IY","created_at":"2026-07-05T04:12:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Y75EN5IYDJZS3KJSGXHJABMEDK","target":"record","payload":{"canonical_record":{"source":{"id":"2204.03238","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-04-07T06:09:47Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"2c5fdd04807c759d8cc2a6aec3ce4d3c31450990fb662f1c72e199edb8bc5e79","abstract_canon_sha256":"7f797850c10fc8e7b7f836350df04667c23f0c22caf924d9a132232b0eb86df2"},"schema_version":"1.0"},"canonical_sha256":"c7fa46f5181a732da93235ce9005841ab1f6b7591e755c81138a342af4213d1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:21.249714Z","signature_b64":"QLfTK+sz6nGvkDR4LYBBDsAt0fJjtcQCBq7KmYzya3tZf4W7Fy8P31UWBH5vP+HX89N8dGUSvMSwSaE/5sDkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7fa46f5181a732da93235ce9005841ab1f6b7591e755c81138a342af4213d1b","last_reissued_at":"2026-07-05T04:12:21.249327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:21.249327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.03238","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":"2026-07-05T04:12:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HHr//qxbwDfJ/cm7Wd0AO4o76GeTcMzqMFCkqSc4oZHg+WJaHXkAcRsL5ABy5POe1Mvw2s380a8KuXDUVgeIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:37:01.171266Z"},"content_sha256":"b19a59886d1bb11ad120c48be316ab98119b6f550066bbb65139307d4f4fb063","schema_version":"1.0","event_id":"sha256:b19a59886d1bb11ad120c48be316ab98119b6f550066bbb65139307d4f4fb063"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Y75EN5IYDJZS3KJSGXHJABMEDK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"eess.AS","authors_text":"Hui Wang, Kun Zhao, Qin Zhang, Yuankun Xie, Yutian Wang","submitted_at":"2022-04-07T06:09:47Z","abstract_excerpt":"In this paper, we propose a novel prosody disentangle method for prosodic Text-to-Speech (TTS) model, which introduces the vector quantization (VQ) method to the auxiliary prosody encoder to obtain the decomposed prosody representations in an unsupervised manner. Rely on its advantages, the speaking styles, such as pitch, speaking velocity, local pitch variance, etc., are decomposed automatically into the latent quantize vectors. We also investigate the internal mechanism of VQ disentangle process by means of a latent variables counter and find that higher value dimensions usually represent pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03238","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/2204.03238/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":"2026-07-05T04:12:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WcCtKQhxmpJWbOOSDGuLhwe0j7nurmoUGxexiuegyiNSf0a2KNcrdm9xDG64vWvbdNKFhBXxPHDt/KkjXr1/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:37:01.172294Z"},"content_sha256":"8838ad241b4a8e74e2469947fc42bab8862d0a45a88a242fb9fc74c23aeb3584","schema_version":"1.0","event_id":"sha256:8838ad241b4a8e74e2469947fc42bab8862d0a45a88a242fb9fc74c23aeb3584"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y75EN5IYDJZS3KJSGXHJABMEDK/bundle.json","state_url":"https://pith.science/pith/Y75EN5IYDJZS3KJSGXHJABMEDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y75EN5IYDJZS3KJSGXHJABMEDK/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":"2026-08-03T20:37:01Z","links":{"resolver":"https://pith.science/pith/Y75EN5IYDJZS3KJSGXHJABMEDK","bundle":"https://pith.science/pith/Y75EN5IYDJZS3KJSGXHJABMEDK/bundle.json","state":"https://pith.science/pith/Y75EN5IYDJZS3KJSGXHJABMEDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y75EN5IYDJZS3KJSGXHJABMEDK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Y75EN5IYDJZS3KJSGXHJABMEDK","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":"7f797850c10fc8e7b7f836350df04667c23f0c22caf924d9a132232b0eb86df2","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-04-07T06:09:47Z","title_canon_sha256":"2c5fdd04807c759d8cc2a6aec3ce4d3c31450990fb662f1c72e199edb8bc5e79"},"schema_version":"1.0","source":{"id":"2204.03238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03238","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03238v1","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03238","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"Y75EN5IYDJZS","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"Y75EN5IYDJZS3KJS","created_at":"2026-07-05T04:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"Y75EN5IY","created_at":"2026-07-05T04:12:21Z"}],"graph_snapshots":[{"event_id":"sha256:8838ad241b4a8e74e2469947fc42bab8862d0a45a88a242fb9fc74c23aeb3584","target":"graph","created_at":"2026-07-05T04:12:21Z","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/2204.03238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel prosody disentangle method for prosodic Text-to-Speech (TTS) model, which introduces the vector quantization (VQ) method to the auxiliary prosody encoder to obtain the decomposed prosody representations in an unsupervised manner. Rely on its advantages, the speaking styles, such as pitch, speaking velocity, local pitch variance, etc., are decomposed automatically into the latent quantize vectors. We also investigate the internal mechanism of VQ disentangle process by means of a latent variables counter and find that higher value dimensions usually represent pr","authors_text":"Hui Wang, Kun Zhao, Qin Zhang, Yuankun Xie, Yutian Wang","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-04-07T06:09:47Z","title":"Unsupervised Quantized Prosody Representation for Controllable Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03238","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:b19a59886d1bb11ad120c48be316ab98119b6f550066bbb65139307d4f4fb063","target":"record","created_at":"2026-07-05T04:12:21Z","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":"7f797850c10fc8e7b7f836350df04667c23f0c22caf924d9a132232b0eb86df2","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-04-07T06:09:47Z","title_canon_sha256":"2c5fdd04807c759d8cc2a6aec3ce4d3c31450990fb662f1c72e199edb8bc5e79"},"schema_version":"1.0","source":{"id":"2204.03238","kind":"arxiv","version":1}},"canonical_sha256":"c7fa46f5181a732da93235ce9005841ab1f6b7591e755c81138a342af4213d1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7fa46f5181a732da93235ce9005841ab1f6b7591e755c81138a342af4213d1b","first_computed_at":"2026-07-05T04:12:21.249327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:21.249327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QLfTK+sz6nGvkDR4LYBBDsAt0fJjtcQCBq7KmYzya3tZf4W7Fy8P31UWBH5vP+HX89N8dGUSvMSwSaE/5sDkDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:21.249714Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b19a59886d1bb11ad120c48be316ab98119b6f550066bbb65139307d4f4fb063","sha256:8838ad241b4a8e74e2469947fc42bab8862d0a45a88a242fb9fc74c23aeb3584"],"state_sha256":"cbf213e3900131d218b94484999aafcdcf99029c1489ffd97f19dbab244af5a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SWx3zw9p0VhDKn786bSr14ES/rU2jeRn9b2pYbb6GJpoQOLTxIAsiLCZbdoyed6fiyylZ0Rqy3x20dQ83Uh4DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:37:01.179174Z","bundle_sha256":"56c2abfa3010fe706de8d30c0788c036e3717e89e8ae26c78b24085c456d43cd"}}