{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:I4ZWVYY5745AO6XWACMWNXNHOG","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":"5735c88b602425f3a61d2a63f8cb70ef4a04c3f72ddae87ae2f105fca31eb830","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-14T18:16:42Z","title_canon_sha256":"8912bcf9b32cec7812a95ea9030ae5fbce9152db0bca676293d6780b7410fe20"},"schema_version":"1.0","source":{"id":"2111.07402","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.07402","created_at":"2026-07-05T05:24:25Z"},{"alias_kind":"arxiv_version","alias_value":"2111.07402v3","created_at":"2026-07-05T05:24:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07402","created_at":"2026-07-05T05:24:25Z"},{"alias_kind":"pith_short_12","alias_value":"I4ZWVYY5745A","created_at":"2026-07-05T05:24:25Z"},{"alias_kind":"pith_short_16","alias_value":"I4ZWVYY5745AO6XW","created_at":"2026-07-05T05:24:25Z"},{"alias_kind":"pith_short_8","alias_value":"I4ZWVYY5","created_at":"2026-07-05T05:24:25Z"}],"graph_snapshots":[{"event_id":"sha256:dcc2725e3b0193c30c05feb725d496fde53850eb07dab21e7371238d6b3f8b3e","target":"graph","created_at":"2026-07-05T05:24:25Z","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/2111.07402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech emotion conversion is the task of modifying the perceived emotion of a speech utterance while preserving the lexical content and speaker identity. In this study, we cast the problem of emotion conversion as a spoken language translation task. We use a decomposition of the speech signal into discrete learned representations, consisting of phonetic-content units, prosodic features, speaker, and emotion. First, we modify the speech content by translating the phonetic-content units to a target emotion, and then predict the prosodic features based on these units. Finally, the speech waveform","authors_text":"Abdelrahman Mohamed, Adam Polyak, Emmanuel Dupoux, Eugene Kharitonov, Felix Kreuk, Jade Copet, Morgane Rivi\\`ere, Tu-Anh Nguyen, Wei-Ning Hsu, Yossi Adi","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-14T18:16:42Z","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07402","kind":"arxiv","version":3},"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:d0d313c900b482777b768e8b8efee9f4650f6a0b625172e2f15902c1c491c98d","target":"record","created_at":"2026-07-05T05:24:25Z","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":"5735c88b602425f3a61d2a63f8cb70ef4a04c3f72ddae87ae2f105fca31eb830","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-14T18:16:42Z","title_canon_sha256":"8912bcf9b32cec7812a95ea9030ae5fbce9152db0bca676293d6780b7410fe20"},"schema_version":"1.0","source":{"id":"2111.07402","kind":"arxiv","version":3}},"canonical_sha256":"47336ae31dff3a077af6009966dda7718e5ee28e8b0ae97ab14e9e7534a9e667","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47336ae31dff3a077af6009966dda7718e5ee28e8b0ae97ab14e9e7534a9e667","first_computed_at":"2026-07-05T05:24:25.174923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:24:25.174923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DMFfCq0WMxQa3Ycd10vUvpim2LalBR+6nzX1zjzRxRimsBVnQJW6SoyxUNcwiveF9hosmhEI5KNwT3jlxf3LCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:24:25.175412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.07402","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0d313c900b482777b768e8b8efee9f4650f6a0b625172e2f15902c1c491c98d","sha256:dcc2725e3b0193c30c05feb725d496fde53850eb07dab21e7371238d6b3f8b3e"],"state_sha256":"755e33754684a8b33ea22920be6ee19d5d9a169e79735a41ab40cecdaaab85d0"}