{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AONT34TR4H3E37E27YJII6G72I","short_pith_number":"pith:AONT34TR","canonical_record":{"source":{"id":"2406.07803","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T01:40:29Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"6cf94c0e73e3a8b8d72f51d368652a04cb9e4d3a6bedd6b318779d4c13a9b113","abstract_canon_sha256":"ee0474a9633d5740e6470d5a93999d27b2bd233935d4a88ac2337dbe4c2954b5"},"schema_version":"1.0"},"canonical_sha256":"039b3df271e1f64dfc9afe128478dfd229accfaf94371e4cfbdbf86c4079e139","source":{"kind":"arxiv","id":"2406.07803","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07803","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07803v2","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07803","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"pith_short_12","alias_value":"AONT34TR4H3E","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"pith_short_16","alias_value":"AONT34TR4H3E37E2","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"pith_short_8","alias_value":"AONT34TR","created_at":"2026-07-05T09:31:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AONT34TR4H3E37E27YJII6G72I","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07803","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T01:40:29Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"6cf94c0e73e3a8b8d72f51d368652a04cb9e4d3a6bedd6b318779d4c13a9b113","abstract_canon_sha256":"ee0474a9633d5740e6470d5a93999d27b2bd233935d4a88ac2337dbe4c2954b5"},"schema_version":"1.0"},"canonical_sha256":"039b3df271e1f64dfc9afe128478dfd229accfaf94371e4cfbdbf86c4079e139","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:04.089411Z","signature_b64":"2RR3fMRqRehUCHa+GHUWJVHCOypHsNbqAKXCJsUIMRFyQEiVqeAQ+IMs9ranKLubkVLkrUsCJsu7ewMlFl4gAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"039b3df271e1f64dfc9afe128478dfd229accfaf94371e4cfbdbf86c4079e139","last_reissued_at":"2026-07-05T09:31:04.088907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:04.088907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07803","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:31:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eRUUcizepPoit6OeGdO7KyacDBROZx9P0iJX/404Y3ZvadPAY9Jw+xvrWoldydI4LXaZzYSLdx9C8Kss6rClBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:57:49.362750Z"},"content_sha256":"21038fabed03ecefe8a8b872b5ca79f27418a9386f3dc4193d3933b626f57766","schema_version":"1.0","event_id":"sha256:21038fabed03ecefe8a8b872b5ca79f27418a9386f3dc4193d3933b626f57766"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AONT34TR4H3E37E27YJII6G72I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Deok-Hyeon Cho, Hyung-Seok Oh, Sang-Hoon Lee, Seong-Whan Lee, Seung-Bin Kim","submitted_at":"2024-06-12T01:40:29Z","abstract_excerpt":"Despite rapid advances in the field of emotional text-to-speech (TTS), recent studies primarily focus on mimicking the average style of a particular emotion. As a result, the ability to manipulate speech emotion remains constrained to several predefined labels, compromising the ability to reflect the nuanced variations of emotion. In this paper, we propose EmoSphere-TTS, which synthesizes expressive emotional speech by using a spherical emotion vector to control the emotional style and intensity of the synthetic speech. Without any human annotation, we use the arousal, valence, and dominance p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07803","kind":"arxiv","version":2},"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/2406.07803/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":"2026-07-05T09:31:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vos87vsJsMMOTDNsyHZG5U95jcp7Q7Tqvo3rWrSHjvvcIFHuuUcxZHFuZmfXIbLZ/QlO/mgIwIZ5iJb6O2KNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T03:57:49.363298Z"},"content_sha256":"926858b543eb9a71464dc5b3ed27971b7ec286808cb600d7687913007135cc65","schema_version":"1.0","event_id":"sha256:926858b543eb9a71464dc5b3ed27971b7ec286808cb600d7687913007135cc65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AONT34TR4H3E37E27YJII6G72I/bundle.json","state_url":"https://pith.science/pith/AONT34TR4H3E37E27YJII6G72I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AONT34TR4H3E37E27YJII6G72I/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":"2026-08-07T03:57:49Z","links":{"resolver":"https://pith.science/pith/AONT34TR4H3E37E27YJII6G72I","bundle":"https://pith.science/pith/AONT34TR4H3E37E27YJII6G72I/bundle.json","state":"https://pith.science/pith/AONT34TR4H3E37E27YJII6G72I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AONT34TR4H3E37E27YJII6G72I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AONT34TR4H3E37E27YJII6G72I","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":"ee0474a9633d5740e6470d5a93999d27b2bd233935d4a88ac2337dbe4c2954b5","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T01:40:29Z","title_canon_sha256":"6cf94c0e73e3a8b8d72f51d368652a04cb9e4d3a6bedd6b318779d4c13a9b113"},"schema_version":"1.0","source":{"id":"2406.07803","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07803","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07803v2","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07803","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"pith_short_12","alias_value":"AONT34TR4H3E","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"pith_short_16","alias_value":"AONT34TR4H3E37E2","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"pith_short_8","alias_value":"AONT34TR","created_at":"2026-07-05T09:31:04Z"}],"graph_snapshots":[{"event_id":"sha256:926858b543eb9a71464dc5b3ed27971b7ec286808cb600d7687913007135cc65","target":"graph","created_at":"2026-07-05T09:31:04Z","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/2406.07803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite rapid advances in the field of emotional text-to-speech (TTS), recent studies primarily focus on mimicking the average style of a particular emotion. As a result, the ability to manipulate speech emotion remains constrained to several predefined labels, compromising the ability to reflect the nuanced variations of emotion. In this paper, we propose EmoSphere-TTS, which synthesizes expressive emotional speech by using a spherical emotion vector to control the emotional style and intensity of the synthetic speech. Without any human annotation, we use the arousal, valence, and dominance p","authors_text":"Deok-Hyeon Cho, Hyung-Seok Oh, Sang-Hoon Lee, Seong-Whan Lee, Seung-Bin Kim","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T01:40:29Z","title":"EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07803","kind":"arxiv","version":2},"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":"sha256:21038fabed03ecefe8a8b872b5ca79f27418a9386f3dc4193d3933b626f57766","target":"record","created_at":"2026-07-05T09:31:04Z","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":"ee0474a9633d5740e6470d5a93999d27b2bd233935d4a88ac2337dbe4c2954b5","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T01:40:29Z","title_canon_sha256":"6cf94c0e73e3a8b8d72f51d368652a04cb9e4d3a6bedd6b318779d4c13a9b113"},"schema_version":"1.0","source":{"id":"2406.07803","kind":"arxiv","version":2}},"canonical_sha256":"039b3df271e1f64dfc9afe128478dfd229accfaf94371e4cfbdbf86c4079e139","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"039b3df271e1f64dfc9afe128478dfd229accfaf94371e4cfbdbf86c4079e139","first_computed_at":"2026-07-05T09:31:04.088907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:04.088907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2RR3fMRqRehUCHa+GHUWJVHCOypHsNbqAKXCJsUIMRFyQEiVqeAQ+IMs9ranKLubkVLkrUsCJsu7ewMlFl4gAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:04.089411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07803","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21038fabed03ecefe8a8b872b5ca79f27418a9386f3dc4193d3933b626f57766","sha256:926858b543eb9a71464dc5b3ed27971b7ec286808cb600d7687913007135cc65"],"state_sha256":"ae77ab40cc9bad43e32454c3152bf13862d577cb1b1a106a98d3611b9539f221"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bfqD0uzt4DJ9vbxXJcv4Y6HNRSLOjR9gzXZlVz+rz8RmHPibF1dr74ttZv8smX4a3vLCOWGl21PObdaynjxwAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T03:57:49.368327Z","bundle_sha256":"3dffcbe192a91d0338842b17489c877abcf3e2d9b98e7f3000e922d73125e7b4"}}