{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RTS57DO6ASERIHOTJHBXTCOBEZ","short_pith_number":"pith:RTS57DO6","canonical_record":{"source":{"id":"2211.02336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-04T09:23:02Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"98a709c14223e999452e4f66b56e8a6280fd4fefdcd5fb29655802c6e1a0bd4a","abstract_canon_sha256":"ff17b731fbd1051dc49e4e27536e15948e23bd3afd1db16b19adfb17cdf81910"},"schema_version":"1.0"},"canonical_sha256":"8ce5df8dde0489141dd349c37989c12650ea327332e0262dc2d937117ef375fa","source":{"kind":"arxiv","id":"2211.02336","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02336","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02336v1","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02336","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"RTS57DO6ASER","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"RTS57DO6ASERIHOT","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"RTS57DO6","created_at":"2026-07-05T05:13:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RTS57DO6ASERIHOTJHBXTCOBEZ","target":"record","payload":{"canonical_record":{"source":{"id":"2211.02336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-04T09:23:02Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"98a709c14223e999452e4f66b56e8a6280fd4fefdcd5fb29655802c6e1a0bd4a","abstract_canon_sha256":"ff17b731fbd1051dc49e4e27536e15948e23bd3afd1db16b19adfb17cdf81910"},"schema_version":"1.0"},"canonical_sha256":"8ce5df8dde0489141dd349c37989c12650ea327332e0262dc2d937117ef375fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:14.342615Z","signature_b64":"yzoxb+fZrpxKbSTrflnB+t49m0NXbAelixHoKn/ONqrh8NVbmHOQcIEj9MEWTrae+Fk6uMc7kczeFT78f2pTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ce5df8dde0489141dd349c37989c12650ea327332e0262dc2d937117ef375fa","last_reissued_at":"2026-07-05T05:13:14.342182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:14.342182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.02336","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":"2026-07-05T05:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/fxKVkbOezsyBOHkeuei6SVRaZptB46zsyMDUq9ODrNsyu5cjrnPebc8t9Kd1mfhJ4PSla98wqFoKQSdnmhYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:25:55.879277Z"},"content_sha256":"3dc9fc88b3cf2240e92b105e56e5d20feb87a71c913f6a5ebf026c4116fd624b","schema_version":"1.0","event_id":"sha256:3dc9fc88b3cf2240e92b105e56e5d20feb87a71c913f6a5ebf026c4116fd624b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RTS57DO6ASERIHOTJHBXTCOBEZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Speech Prosody of Audiobook Text-to-Speech Synthesis with Acoustic and Textual Contexts","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Ashish Kulkarni, Detai Xin, Federico Ang, Hiroshi Saruwatari, Sharath Adavanne, Shinnosuke Takamichi","submitted_at":"2022-11-04T09:23:02Z","abstract_excerpt":"We present a multi-speaker Japanese audiobook text-to-speech (TTS) system that leverages multimodal context information of preceding acoustic context and bilateral textual context to improve the prosody of synthetic speech. Previous work either uses unilateral or single-modality context, which does not fully represent the context information. The proposed method uses an acoustic context encoder and a textual context encoder to aggregate context information and feeds it to the TTS model, which enables the model to predict context-dependent prosody. We conducted comprehensive objective and subje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02336","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/2211.02336/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":"2026-07-05T05:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TNs/Zs53/g8lgw7wR3+xdodK+l8pGZ9vqyTa9Rf2Qd0Pl9UC/vSQdGfroemj55OrIl+zwm3X4Y+zR/ZoMwZ4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:25:55.879661Z"},"content_sha256":"d25061199b02c793d1989d02874008aa67e2ea745ea08ee48243d436f268ee06","schema_version":"1.0","event_id":"sha256:d25061199b02c793d1989d02874008aa67e2ea745ea08ee48243d436f268ee06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/bundle.json","state_url":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/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":"2026-07-06T08:25:55Z","links":{"resolver":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ","bundle":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/bundle.json","state":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RTS57DO6ASERIHOTJHBXTCOBEZ","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":"ff17b731fbd1051dc49e4e27536e15948e23bd3afd1db16b19adfb17cdf81910","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-04T09:23:02Z","title_canon_sha256":"98a709c14223e999452e4f66b56e8a6280fd4fefdcd5fb29655802c6e1a0bd4a"},"schema_version":"1.0","source":{"id":"2211.02336","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.02336","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2211.02336v1","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02336","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"RTS57DO6ASER","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"RTS57DO6ASERIHOT","created_at":"2026-07-05T05:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"RTS57DO6","created_at":"2026-07-05T05:13:14Z"}],"graph_snapshots":[{"event_id":"sha256:d25061199b02c793d1989d02874008aa67e2ea745ea08ee48243d436f268ee06","target":"graph","created_at":"2026-07-05T05:13:14Z","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/2211.02336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a multi-speaker Japanese audiobook text-to-speech (TTS) system that leverages multimodal context information of preceding acoustic context and bilateral textual context to improve the prosody of synthetic speech. Previous work either uses unilateral or single-modality context, which does not fully represent the context information. The proposed method uses an acoustic context encoder and a textual context encoder to aggregate context information and feeds it to the TTS model, which enables the model to predict context-dependent prosody. We conducted comprehensive objective and subje","authors_text":"Ashish Kulkarni, Detai Xin, Federico Ang, Hiroshi Saruwatari, Sharath Adavanne, Shinnosuke Takamichi","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-04T09:23:02Z","title":"Improving Speech Prosody of Audiobook Text-to-Speech Synthesis with Acoustic and Textual Contexts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02336","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":"sha256:3dc9fc88b3cf2240e92b105e56e5d20feb87a71c913f6a5ebf026c4116fd624b","target":"record","created_at":"2026-07-05T05:13:14Z","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":"ff17b731fbd1051dc49e4e27536e15948e23bd3afd1db16b19adfb17cdf81910","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-04T09:23:02Z","title_canon_sha256":"98a709c14223e999452e4f66b56e8a6280fd4fefdcd5fb29655802c6e1a0bd4a"},"schema_version":"1.0","source":{"id":"2211.02336","kind":"arxiv","version":1}},"canonical_sha256":"8ce5df8dde0489141dd349c37989c12650ea327332e0262dc2d937117ef375fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ce5df8dde0489141dd349c37989c12650ea327332e0262dc2d937117ef375fa","first_computed_at":"2026-07-05T05:13:14.342182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:14.342182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yzoxb+fZrpxKbSTrflnB+t49m0NXbAelixHoKn/ONqrh8NVbmHOQcIEj9MEWTrae+Fk6uMc7kczeFT78f2pTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:14.342615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.02336","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dc9fc88b3cf2240e92b105e56e5d20feb87a71c913f6a5ebf026c4116fd624b","sha256:d25061199b02c793d1989d02874008aa67e2ea745ea08ee48243d436f268ee06"],"state_sha256":"bed2969ca7d54d0804a82e81cae5bea867ca03177e4366936fb89338a581e2a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4U/oXcuPJeaD2qXvvDkt1RKMDA8UmU5uvdPZwlziyOCPwXJhsH99W6yQYU6ZRgxro80MvfMkzf4M+HK6OaBZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:25:55.881699Z","bundle_sha256":"772f251a242c069f2e57b7b5923c20e17d6473bb48f5c0090a5ec3db9181a6ec"}}