{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V54Z5UGTOYTKQD74PQKNLYTMRH","short_pith_number":"pith:V54Z5UGT","canonical_record":{"source":{"id":"2409.10157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T10:41:36Z","cross_cats_sorted":["cs.SD","eess.SP"],"title_canon_sha256":"cd9a2f6fb119be3ded9b101ff45a7f80f09dc89f8eaee29b800c1d3795cddb86","abstract_canon_sha256":"329d6126eab61c3fb033d649bbac44fbfde532b8dce0c0d36f7bca4d6de271e1"},"schema_version":"1.0"},"canonical_sha256":"af799ed0d37626a80ffc7c14d5e26c89c3a194afaa211fb24d8029f5c9f5a61f","source":{"kind":"arxiv","id":"2409.10157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10157","created_at":"2026-07-05T09:07:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10157v1","created_at":"2026-07-05T09:07:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10157","created_at":"2026-07-05T09:07:36Z"},{"alias_kind":"pith_short_12","alias_value":"V54Z5UGTOYTK","created_at":"2026-07-05T09:07:36Z"},{"alias_kind":"pith_short_16","alias_value":"V54Z5UGTOYTKQD74","created_at":"2026-07-05T09:07:36Z"},{"alias_kind":"pith_short_8","alias_value":"V54Z5UGT","created_at":"2026-07-05T09:07:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V54Z5UGTOYTKQD74PQKNLYTMRH","target":"record","payload":{"canonical_record":{"source":{"id":"2409.10157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T10:41:36Z","cross_cats_sorted":["cs.SD","eess.SP"],"title_canon_sha256":"cd9a2f6fb119be3ded9b101ff45a7f80f09dc89f8eaee29b800c1d3795cddb86","abstract_canon_sha256":"329d6126eab61c3fb033d649bbac44fbfde532b8dce0c0d36f7bca4d6de271e1"},"schema_version":"1.0"},"canonical_sha256":"af799ed0d37626a80ffc7c14d5e26c89c3a194afaa211fb24d8029f5c9f5a61f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:36.011122Z","signature_b64":"DgCpjKTZYsAU2bLP8ygUh6pOl3begLjhunJnD8RuRYhpUWCLM5MgtPOFDz5ARIxhd3KwMi5cOmiL3COwGBHDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af799ed0d37626a80ffc7c14d5e26c89c3a194afaa211fb24d8029f5c9f5a61f","last_reissued_at":"2026-07-05T09:07:36.010666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:36.010666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.10157","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":"2026-07-05T09:07:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dGwdNGBE79UItQWGTZHiXQXJMI1J9w2Fa02ITRLwerwxuMxpz9GORy6YiYjih78XQFMZMNEyZBaPw64T7yMHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:31:00.498847Z"},"content_sha256":"52d4fd71060320753c634345278f3c6ce1b23c227bfaf802a92377b275557fd5","schema_version":"1.0","event_id":"sha256:52d4fd71060320753c634345278f3c6ce1b23c227bfaf802a92377b275557fd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V54Z5UGTOYTKQD74PQKNLYTMRH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Chen Zhang, Huayun Zhang, Nancy F. Chen, Xiaoxue Gao, Yiming Chen","submitted_at":"2024-09-16T10:41:36Z","abstract_excerpt":"Current emotional text-to-speech (TTS) models predominantly conduct supervised training to learn the conversion from text and desired emotion to its emotional speech, focusing on a single emotion per text-speech pair. These models only learn the correct emotional outputs without fully comprehending other emotion characteristics, which limits their capabilities of capturing the nuances between different emotions. We propose a controllable Emo-DPO approach, which employs direct preference optimization to differentiate subtle emotional nuances between emotions through optimizing towards preferred"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10157","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/2409.10157/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":"2026-07-05T09:07:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"isR4SupNwO7piuP/Ua/9ID3WHZChdkxdJLpjOuPvpw/TxoPSYMN4DnFRZ1c30qUAkdveUS5geDyCPT8KVXO5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:31:00.499475Z"},"content_sha256":"96da7b3f8075740ea48df5b97dbe9ae97b910ecb703f7fa8c310b47f72670948","schema_version":"1.0","event_id":"sha256:96da7b3f8075740ea48df5b97dbe9ae97b910ecb703f7fa8c310b47f72670948"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/bundle.json","state_url":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/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":"2026-08-10T06:31:00Z","links":{"resolver":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH","bundle":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/bundle.json","state":"https://pith.science/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V54Z5UGTOYTKQD74PQKNLYTMRH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V54Z5UGTOYTKQD74PQKNLYTMRH","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":"329d6126eab61c3fb033d649bbac44fbfde532b8dce0c0d36f7bca4d6de271e1","cross_cats_sorted":["cs.SD","eess.SP"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T10:41:36Z","title_canon_sha256":"cd9a2f6fb119be3ded9b101ff45a7f80f09dc89f8eaee29b800c1d3795cddb86"},"schema_version":"1.0","source":{"id":"2409.10157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10157","created_at":"2026-07-05T09:07:36Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10157v1","created_at":"2026-07-05T09:07:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10157","created_at":"2026-07-05T09:07:36Z"},{"alias_kind":"pith_short_12","alias_value":"V54Z5UGTOYTK","created_at":"2026-07-05T09:07:36Z"},{"alias_kind":"pith_short_16","alias_value":"V54Z5UGTOYTKQD74","created_at":"2026-07-05T09:07:36Z"},{"alias_kind":"pith_short_8","alias_value":"V54Z5UGT","created_at":"2026-07-05T09:07:36Z"}],"graph_snapshots":[{"event_id":"sha256:96da7b3f8075740ea48df5b97dbe9ae97b910ecb703f7fa8c310b47f72670948","target":"graph","created_at":"2026-07-05T09:07:36Z","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/2409.10157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current emotional text-to-speech (TTS) models predominantly conduct supervised training to learn the conversion from text and desired emotion to its emotional speech, focusing on a single emotion per text-speech pair. These models only learn the correct emotional outputs without fully comprehending other emotion characteristics, which limits their capabilities of capturing the nuances between different emotions. We propose a controllable Emo-DPO approach, which employs direct preference optimization to differentiate subtle emotional nuances between emotions through optimizing towards preferred","authors_text":"Chen Zhang, Huayun Zhang, Nancy F. Chen, Xiaoxue Gao, Yiming Chen","cross_cats":["cs.SD","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T10:41:36Z","title":"Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10157","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":"sha256:52d4fd71060320753c634345278f3c6ce1b23c227bfaf802a92377b275557fd5","target":"record","created_at":"2026-07-05T09:07:36Z","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":"329d6126eab61c3fb033d649bbac44fbfde532b8dce0c0d36f7bca4d6de271e1","cross_cats_sorted":["cs.SD","eess.SP"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T10:41:36Z","title_canon_sha256":"cd9a2f6fb119be3ded9b101ff45a7f80f09dc89f8eaee29b800c1d3795cddb86"},"schema_version":"1.0","source":{"id":"2409.10157","kind":"arxiv","version":1}},"canonical_sha256":"af799ed0d37626a80ffc7c14d5e26c89c3a194afaa211fb24d8029f5c9f5a61f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af799ed0d37626a80ffc7c14d5e26c89c3a194afaa211fb24d8029f5c9f5a61f","first_computed_at":"2026-07-05T09:07:36.010666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:36.010666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DgCpjKTZYsAU2bLP8ygUh6pOl3begLjhunJnD8RuRYhpUWCLM5MgtPOFDz5ARIxhd3KwMi5cOmiL3COwGBHDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:36.011122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.10157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52d4fd71060320753c634345278f3c6ce1b23c227bfaf802a92377b275557fd5","sha256:96da7b3f8075740ea48df5b97dbe9ae97b910ecb703f7fa8c310b47f72670948"],"state_sha256":"39db23262ac12af57a83e6667fbe476baf0da99ddf68356ddcbfa7e84e0a3109"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vv8q3xoyDx38TTn08OoKkmlM6C3QNjCIBtUrOexvXTUxKmX0LilhfmwCIjcHMWgIrYfr6LHaRcqvAykairVpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:31:00.508391Z","bundle_sha256":"662c25945f7dcda94bf9a06913e3c005683478efd5bd23d368be6d444357d123"}}