{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H45GVSFTQLLM525DI5ZW7K6CE7","short_pith_number":"pith:H45GVSFT","schema_version":"1.0","canonical_sha256":"3f3a6ac8b382d6ceeba347736fabc227eaf31c2c983d025f59f2a723eeb792a8","source":{"kind":"arxiv","id":"2206.14866","version":2},"attestation_state":"computed","paper":{"title":"iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"eess.AS","authors_text":"Feijun Jiang, Guangyan Zhang, Jialun Wu, Mei Li, Tan Lee, Wenjie Zhang, Ying Qin, Yutao Gai","submitted_at":"2022-06-29T19:11:42Z","abstract_excerpt":"The capability of generating speech with specific type of emotion is desired for many applications of human-computer interaction. Cross-speaker emotion transfer is a common approach to generating emotional speech when speech with emotion labels from target speakers is not available for model training. This paper presents a novel cross-speaker emotion transfer system, named iEmoTTS. The system is composed of an emotion encoder, a prosody predictor, and a timbre encoder. The emotion encoder extracts the identity of emotion type as well as the respective emotion intensity from the mel-spectrogram"},"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":"2206.14866","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-06-29T19:11:42Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"da3a5364be63caa3cdb61b766d757138d80618a69e3c32c4189a785d4beedaee","abstract_canon_sha256":"e2ea8a37da81c753a8524c5b951da83939a84171d7569ddb4ab8b253b5c8520f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:30.078145Z","signature_b64":"iUAztFs7SD9ZiFXiuQwzRDXUTQvUjO5SZ+7wAo6pwaWzyP7cXpIIB2bgkMIiWVTbF/B4xW7bPUYUyb9sj8+SBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f3a6ac8b382d6ceeba347736fabc227eaf31c2c983d025f59f2a723eeb792a8","last_reissued_at":"2026-07-05T05:30:30.077759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:30.077759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis based on Disentanglement between Prosody and Timbre","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"eess.AS","authors_text":"Feijun Jiang, Guangyan Zhang, Jialun Wu, Mei Li, Tan Lee, Wenjie Zhang, Ying Qin, Yutao Gai","submitted_at":"2022-06-29T19:11:42Z","abstract_excerpt":"The capability of generating speech with specific type of emotion is desired for many applications of human-computer interaction. Cross-speaker emotion transfer is a common approach to generating emotional speech when speech with emotion labels from target speakers is not available for model training. This paper presents a novel cross-speaker emotion transfer system, named iEmoTTS. The system is composed of an emotion encoder, a prosody predictor, and a timbre encoder. The emotion encoder extracts the identity of emotion type as well as the respective emotion intensity from the mel-spectrogram"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.14866","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/2206.14866/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":"2206.14866","created_at":"2026-07-05T05:30:30.077810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.14866v2","created_at":"2026-07-05T05:30:30.077810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.14866","created_at":"2026-07-05T05:30:30.077810+00:00"},{"alias_kind":"pith_short_12","alias_value":"H45GVSFTQLLM","created_at":"2026-07-05T05:30:30.077810+00:00"},{"alias_kind":"pith_short_16","alias_value":"H45GVSFTQLLM525D","created_at":"2026-07-05T05:30:30.077810+00:00"},{"alias_kind":"pith_short_8","alias_value":"H45GVSFT","created_at":"2026-07-05T05:30:30.077810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04598","citing_title":"Multi-Step Prediction and Control of Hierarchical Emotion Distribution in Text-to-Speech Synthesis","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H45GVSFTQLLM525DI5ZW7K6CE7","json":"https://pith.science/pith/H45GVSFTQLLM525DI5ZW7K6CE7.json","graph_json":"https://pith.science/api/pith-number/H45GVSFTQLLM525DI5ZW7K6CE7/graph.json","events_json":"https://pith.science/api/pith-number/H45GVSFTQLLM525DI5ZW7K6CE7/events.json","paper":"https://pith.science/paper/H45GVSFT"},"agent_actions":{"view_html":"https://pith.science/pith/H45GVSFTQLLM525DI5ZW7K6CE7","download_json":"https://pith.science/pith/H45GVSFTQLLM525DI5ZW7K6CE7.json","view_paper":"https://pith.science/paper/H45GVSFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.14866&json=true","fetch_graph":"https://pith.science/api/pith-number/H45GVSFTQLLM525DI5ZW7K6CE7/graph.json","fetch_events":"https://pith.science/api/pith-number/H45GVSFTQLLM525DI5ZW7K6CE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H45GVSFTQLLM525DI5ZW7K6CE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H45GVSFTQLLM525DI5ZW7K6CE7/action/storage_attestation","attest_author":"https://pith.science/pith/H45GVSFTQLLM525DI5ZW7K6CE7/action/author_attestation","sign_citation":"https://pith.science/pith/H45GVSFTQLLM525DI5ZW7K6CE7/action/citation_signature","submit_replication":"https://pith.science/pith/H45GVSFTQLLM525DI5ZW7K6CE7/action/replication_record"}},"created_at":"2026-07-05T05:30:30.077810+00:00","updated_at":"2026-07-05T05:30:30.077810+00:00"}