{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BIWN4XT3TL4GVRVVRQZALXTFNA","short_pith_number":"pith:BIWN4XT3","schema_version":"1.0","canonical_sha256":"0a2cde5e7b9af86ac6b58c3205de65680eec456a2324d0f3a56324e8a5ff00d0","source":{"kind":"arxiv","id":"2211.09496","version":2},"attestation_state":"computed","paper":{"title":"EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenpeng Du, Kai Yu, Xie Chen, Yiwei Guo","submitted_at":"2022-11-17T12:37:48Z","abstract_excerpt":"Although current neural text-to-speech (TTS) models are able to generate high-quality speech, intensity controllable emotional TTS is still a challenging task. Most existing methods need external optimizations for intensity calculation, leading to suboptimal results or degraded quality. In this paper, we propose EmoDiff, a diffusion-based TTS model where emotion intensity can be manipulated by a proposed soft-label guidance technique derived from classifier guidance. Specifically, instead of being guided with a one-hot vector for the specified emotion, EmoDiff is guided with a soft label where"},"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":"2211.09496","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-17T12:37:48Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.SD"],"title_canon_sha256":"c8439de8b1e4a03cb31aefa5539c18d537f297f29e19cf8ab23839a97f92b036","abstract_canon_sha256":"10ba0c7127b7b1ad3ac15c390f04eede8628633b11c1983622bd04bbadc7db36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:42:29.046078Z","signature_b64":"+o8EKsDKSJE+38D6Fmbuvqzf/xl9Y1BqbemCwGVdIsZ21TZPpHufCeNnjlvudwviurC376T0z6VTncz1xu6WCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a2cde5e7b9af86ac6b58c3205de65680eec456a2324d0f3a56324e8a5ff00d0","last_reissued_at":"2026-07-05T05:42:29.045659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:42:29.045659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenpeng Du, Kai Yu, Xie Chen, Yiwei Guo","submitted_at":"2022-11-17T12:37:48Z","abstract_excerpt":"Although current neural text-to-speech (TTS) models are able to generate high-quality speech, intensity controllable emotional TTS is still a challenging task. Most existing methods need external optimizations for intensity calculation, leading to suboptimal results or degraded quality. In this paper, we propose EmoDiff, a diffusion-based TTS model where emotion intensity can be manipulated by a proposed soft-label guidance technique derived from classifier guidance. Specifically, instead of being guided with a one-hot vector for the specified emotion, EmoDiff is guided with a soft label where"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09496","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/2211.09496/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":"2211.09496","created_at":"2026-07-05T05:42:29.045724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09496v2","created_at":"2026-07-05T05:42:29.045724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09496","created_at":"2026-07-05T05:42:29.045724+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIWN4XT3TL4G","created_at":"2026-07-05T05:42:29.045724+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIWN4XT3TL4GVRVV","created_at":"2026-07-05T05:42:29.045724+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIWN4XT3","created_at":"2026-07-05T05:42:29.045724+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/BIWN4XT3TL4GVRVVRQZALXTFNA","json":"https://pith.science/pith/BIWN4XT3TL4GVRVVRQZALXTFNA.json","graph_json":"https://pith.science/api/pith-number/BIWN4XT3TL4GVRVVRQZALXTFNA/graph.json","events_json":"https://pith.science/api/pith-number/BIWN4XT3TL4GVRVVRQZALXTFNA/events.json","paper":"https://pith.science/paper/BIWN4XT3"},"agent_actions":{"view_html":"https://pith.science/pith/BIWN4XT3TL4GVRVVRQZALXTFNA","download_json":"https://pith.science/pith/BIWN4XT3TL4GVRVVRQZALXTFNA.json","view_paper":"https://pith.science/paper/BIWN4XT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09496&json=true","fetch_graph":"https://pith.science/api/pith-number/BIWN4XT3TL4GVRVVRQZALXTFNA/graph.json","fetch_events":"https://pith.science/api/pith-number/BIWN4XT3TL4GVRVVRQZALXTFNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIWN4XT3TL4GVRVVRQZALXTFNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIWN4XT3TL4GVRVVRQZALXTFNA/action/storage_attestation","attest_author":"https://pith.science/pith/BIWN4XT3TL4GVRVVRQZALXTFNA/action/author_attestation","sign_citation":"https://pith.science/pith/BIWN4XT3TL4GVRVVRQZALXTFNA/action/citation_signature","submit_replication":"https://pith.science/pith/BIWN4XT3TL4GVRVVRQZALXTFNA/action/replication_record"}},"created_at":"2026-07-05T05:42:29.045724+00:00","updated_at":"2026-07-05T05:42:29.045724+00:00"}