{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RTS57DO6ASERIHOTJHBXTCOBEZ","short_pith_number":"pith:RTS57DO6","schema_version":"1.0","canonical_sha256":"8ce5df8dde0489141dd349c37989c12650ea327332e0262dc2d937117ef375fa","source":{"kind":"arxiv","id":"2211.02336","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.02336","created_at":"2026-07-05T05:13:14.342247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02336v1","created_at":"2026-07-05T05:13:14.342247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02336","created_at":"2026-07-05T05:13:14.342247+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTS57DO6ASER","created_at":"2026-07-05T05:13:14.342247+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTS57DO6ASERIHOT","created_at":"2026-07-05T05:13:14.342247+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTS57DO6","created_at":"2026-07-05T05:13:14.342247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ","json":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ.json","graph_json":"https://pith.science/api/pith-number/RTS57DO6ASERIHOTJHBXTCOBEZ/graph.json","events_json":"https://pith.science/api/pith-number/RTS57DO6ASERIHOTJHBXTCOBEZ/events.json","paper":"https://pith.science/paper/RTS57DO6"},"agent_actions":{"view_html":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ","download_json":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ.json","view_paper":"https://pith.science/paper/RTS57DO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02336&json=true","fetch_graph":"https://pith.science/api/pith-number/RTS57DO6ASERIHOTJHBXTCOBEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RTS57DO6ASERIHOTJHBXTCOBEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/action/storage_attestation","attest_author":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/action/author_attestation","sign_citation":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/action/citation_signature","submit_replication":"https://pith.science/pith/RTS57DO6ASERIHOTJHBXTCOBEZ/action/replication_record"}},"created_at":"2026-07-05T05:13:14.342247+00:00","updated_at":"2026-07-05T05:13:14.342247+00:00"}