{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BIWN4XT3TL4GVRVVRQZALXTFNA","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":"10ba0c7127b7b1ad3ac15c390f04eede8628633b11c1983622bd04bbadc7db36","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-17T12:37:48Z","title_canon_sha256":"c8439de8b1e4a03cb31aefa5539c18d537f297f29e19cf8ab23839a97f92b036"},"schema_version":"1.0","source":{"id":"2211.09496","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09496","created_at":"2026-07-05T05:42:29Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09496v2","created_at":"2026-07-05T05:42:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09496","created_at":"2026-07-05T05:42:29Z"},{"alias_kind":"pith_short_12","alias_value":"BIWN4XT3TL4G","created_at":"2026-07-05T05:42:29Z"},{"alias_kind":"pith_short_16","alias_value":"BIWN4XT3TL4GVRVV","created_at":"2026-07-05T05:42:29Z"},{"alias_kind":"pith_short_8","alias_value":"BIWN4XT3","created_at":"2026-07-05T05:42:29Z"}],"graph_snapshots":[{"event_id":"sha256:a6366445b0153b232ce37fa69c440e90498703cc7a3ac995f5af8987ef18dfdb","target":"graph","created_at":"2026-07-05T05:42:29Z","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/2211.09496/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenpeng Du, Kai Yu, Xie Chen, Yiwei Guo","cross_cats":["cs.AI","cs.HC","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-17T12:37:48Z","title":"EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09496","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:b009d04aa14c37276bde808ec83bdaee87a319d56404800c773573629b422611","target":"record","created_at":"2026-07-05T05:42:29Z","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":"10ba0c7127b7b1ad3ac15c390f04eede8628633b11c1983622bd04bbadc7db36","cross_cats_sorted":["cs.AI","cs.HC","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-17T12:37:48Z","title_canon_sha256":"c8439de8b1e4a03cb31aefa5539c18d537f297f29e19cf8ab23839a97f92b036"},"schema_version":"1.0","source":{"id":"2211.09496","kind":"arxiv","version":2}},"canonical_sha256":"0a2cde5e7b9af86ac6b58c3205de65680eec456a2324d0f3a56324e8a5ff00d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a2cde5e7b9af86ac6b58c3205de65680eec456a2324d0f3a56324e8a5ff00d0","first_computed_at":"2026-07-05T05:42:29.045659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:42:29.045659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+o8EKsDKSJE+38D6Fmbuvqzf/xl9Y1BqbemCwGVdIsZ21TZPpHufCeNnjlvudwviurC376T0z6VTncz1xu6WCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:42:29.046078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09496","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b009d04aa14c37276bde808ec83bdaee87a319d56404800c773573629b422611","sha256:a6366445b0153b232ce37fa69c440e90498703cc7a3ac995f5af8987ef18dfdb"],"state_sha256":"8a7574380ee11e5f04118f636d9870c8dc21a21d32b810731dc9b21204ac5bf1"}