{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XUK52S7HVJGULPKRTEOT4XCYVB","short_pith_number":"pith:XUK52S7H","canonical_record":{"source":{"id":"2401.08166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-16T07:13:16Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"2af292c55cccda951a9dbc77ba6217f548bdb2ac38d95c65f8c67d236bceb338","abstract_canon_sha256":"cde82165cf51f2e89b01bb8816f86be3b7e6f13de78551e844c01d3029b26916"},"schema_version":"1.0"},"canonical_sha256":"bd15dd4be7aa4d45bd51991d3e5c58a86324635327b744fa2d06d80abce06814","source":{"kind":"arxiv","id":"2401.08166","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08166","created_at":"2026-07-05T07:34:08Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08166v1","created_at":"2026-07-05T07:34:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08166","created_at":"2026-07-05T07:34:08Z"},{"alias_kind":"pith_short_12","alias_value":"XUK52S7HVJGU","created_at":"2026-07-05T07:34:08Z"},{"alias_kind":"pith_short_16","alias_value":"XUK52S7HVJGULPKR","created_at":"2026-07-05T07:34:08Z"},{"alias_kind":"pith_short_8","alias_value":"XUK52S7H","created_at":"2026-07-05T07:34:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XUK52S7HVJGULPKRTEOT4XCYVB","target":"record","payload":{"canonical_record":{"source":{"id":"2401.08166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-16T07:13:16Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"2af292c55cccda951a9dbc77ba6217f548bdb2ac38d95c65f8c67d236bceb338","abstract_canon_sha256":"cde82165cf51f2e89b01bb8816f86be3b7e6f13de78551e844c01d3029b26916"},"schema_version":"1.0"},"canonical_sha256":"bd15dd4be7aa4d45bd51991d3e5c58a86324635327b744fa2d06d80abce06814","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:08.372177Z","signature_b64":"eMfl/BjfDKGf3l91MmUuEG0Zr+Vqed/l9awWow2ZBDnxt+/q7mGHG1pI/o6Ssbeyn+cVhUNRpuxZbKo4aoZYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd15dd4be7aa4d45bd51991d3e5c58a86324635327b744fa2d06d80abce06814","last_reissued_at":"2026-07-05T07:34:08.371786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:08.371786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.08166","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":"2026-07-05T07:34:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BRTGEzCbT1Gpor2ga2AaJewl83fGBAD/jM+L/48aUFSTTmBfAsAKfZqxGxSwnNjww62Dcg0bOZclT0OSchMQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:24:55.535799Z"},"content_sha256":"e98beafd703944f82221bd2dce262f8e29a419ecdb7855fa37d8c8ba538d9e2d","schema_version":"1.0","event_id":"sha256:e98beafd703944f82221bd2dce262f8e29a419ecdb7855fa37d8c8ba538d9e2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XUK52S7HVJGULPKRTEOT4XCYVB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haobin Tang, Jianzong Wang, Jing Xiao, Ning Cheng, Xulong Zhang","submitted_at":"2024-01-16T07:13:16Z","abstract_excerpt":"Existing emotional speech synthesis methods often utilize an utterance-level style embedding extracted from reference audio, neglecting the inherent multi-scale property of speech prosody. We introduce ED-TTS, a multi-scale emotional speech synthesis model that leverages Speech Emotion Diarization (SED) and Speech Emotion Recognition (SER) to model emotions at different levels. Specifically, our proposed approach integrates the utterance-level emotion embedding extracted by SER with fine-grained frame-level emotion embedding obtained from SED. These embeddings are used to condition the reverse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08166","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/2401.08166/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":"2026-07-05T07:34:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wmQQm3wF/wHNOJZy6YHpTkjDrgJsgiEVEu7PbkjbtRi0zL2slKjbhhR5AzGT6H37icnbeDDQmIuz406owiY0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:24:55.536702Z"},"content_sha256":"b99216bf471f0e80d5ef46b47e4b35b27b2dba63d38a72c7628ed153945e4369","schema_version":"1.0","event_id":"sha256:b99216bf471f0e80d5ef46b47e4b35b27b2dba63d38a72c7628ed153945e4369"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XUK52S7HVJGULPKRTEOT4XCYVB/bundle.json","state_url":"https://pith.science/pith/XUK52S7HVJGULPKRTEOT4XCYVB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XUK52S7HVJGULPKRTEOT4XCYVB/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":"2026-08-15T10:24:55Z","links":{"resolver":"https://pith.science/pith/XUK52S7HVJGULPKRTEOT4XCYVB","bundle":"https://pith.science/pith/XUK52S7HVJGULPKRTEOT4XCYVB/bundle.json","state":"https://pith.science/pith/XUK52S7HVJGULPKRTEOT4XCYVB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XUK52S7HVJGULPKRTEOT4XCYVB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XUK52S7HVJGULPKRTEOT4XCYVB","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":"cde82165cf51f2e89b01bb8816f86be3b7e6f13de78551e844c01d3029b26916","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-16T07:13:16Z","title_canon_sha256":"2af292c55cccda951a9dbc77ba6217f548bdb2ac38d95c65f8c67d236bceb338"},"schema_version":"1.0","source":{"id":"2401.08166","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08166","created_at":"2026-07-05T07:34:08Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08166v1","created_at":"2026-07-05T07:34:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08166","created_at":"2026-07-05T07:34:08Z"},{"alias_kind":"pith_short_12","alias_value":"XUK52S7HVJGU","created_at":"2026-07-05T07:34:08Z"},{"alias_kind":"pith_short_16","alias_value":"XUK52S7HVJGULPKR","created_at":"2026-07-05T07:34:08Z"},{"alias_kind":"pith_short_8","alias_value":"XUK52S7H","created_at":"2026-07-05T07:34:08Z"}],"graph_snapshots":[{"event_id":"sha256:b99216bf471f0e80d5ef46b47e4b35b27b2dba63d38a72c7628ed153945e4369","target":"graph","created_at":"2026-07-05T07:34:08Z","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/2401.08166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing emotional speech synthesis methods often utilize an utterance-level style embedding extracted from reference audio, neglecting the inherent multi-scale property of speech prosody. We introduce ED-TTS, a multi-scale emotional speech synthesis model that leverages Speech Emotion Diarization (SED) and Speech Emotion Recognition (SER) to model emotions at different levels. Specifically, our proposed approach integrates the utterance-level emotion embedding extracted by SER with fine-grained frame-level emotion embedding obtained from SED. These embeddings are used to condition the reverse","authors_text":"Haobin Tang, Jianzong Wang, Jing Xiao, Ning Cheng, Xulong Zhang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-16T07:13:16Z","title":"ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08166","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:e98beafd703944f82221bd2dce262f8e29a419ecdb7855fa37d8c8ba538d9e2d","target":"record","created_at":"2026-07-05T07:34:08Z","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":"cde82165cf51f2e89b01bb8816f86be3b7e6f13de78551e844c01d3029b26916","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-16T07:13:16Z","title_canon_sha256":"2af292c55cccda951a9dbc77ba6217f548bdb2ac38d95c65f8c67d236bceb338"},"schema_version":"1.0","source":{"id":"2401.08166","kind":"arxiv","version":1}},"canonical_sha256":"bd15dd4be7aa4d45bd51991d3e5c58a86324635327b744fa2d06d80abce06814","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd15dd4be7aa4d45bd51991d3e5c58a86324635327b744fa2d06d80abce06814","first_computed_at":"2026-07-05T07:34:08.371786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:08.371786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eMfl/BjfDKGf3l91MmUuEG0Zr+Vqed/l9awWow2ZBDnxt+/q7mGHG1pI/o6Ssbeyn+cVhUNRpuxZbKo4aoZYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:08.372177Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08166","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e98beafd703944f82221bd2dce262f8e29a419ecdb7855fa37d8c8ba538d9e2d","sha256:b99216bf471f0e80d5ef46b47e4b35b27b2dba63d38a72c7628ed153945e4369"],"state_sha256":"398cb871aaa76cbca2bd36e2fd4524c50432804315c5cffa4fa2b9b32e321785"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e6xMKKje7/1UKg9UuZ+V+LGbvhrdaUyFisXpyVRaRlvpZ9aOHzHiNus6+Hezxn5yZSiiMb+oSATYIm6ZICLqDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:24:55.541570Z","bundle_sha256":"861456271a94fbae0fa77ffde071da17f6508c1b16b88a9c5b71507d04a8fcd6"}}