{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I4ZWVYY5745AO6XWACMWNXNHOG","short_pith_number":"pith:I4ZWVYY5","schema_version":"1.0","canonical_sha256":"47336ae31dff3a077af6009966dda7718e5ee28e8b0ae97ab14e9e7534a9e667","source":{"kind":"arxiv","id":"2111.07402","version":3},"attestation_state":"computed","paper":{"title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","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","submitted_at":"2021-11-14T18:16:42Z","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"},"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":"2111.07402","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-14T18:16:42Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8912bcf9b32cec7812a95ea9030ae5fbce9152db0bca676293d6780b7410fe20","abstract_canon_sha256":"5735c88b602425f3a61d2a63f8cb70ef4a04c3f72ddae87ae2f105fca31eb830"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:24:25.175412Z","signature_b64":"DMFfCq0WMxQa3Ycd10vUvpim2LalBR+6nzX1zjzRxRimsBVnQJW6SoyxUNcwiveF9hosmhEI5KNwT3jlxf3LCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47336ae31dff3a077af6009966dda7718e5ee28e8b0ae97ab14e9e7534a9e667","last_reissued_at":"2026-07-05T05:24:25.174923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:24:25.174923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","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","submitted_at":"2021-11-14T18:16:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07402","kind":"arxiv","version":3},"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/2111.07402/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":"2111.07402","created_at":"2026-07-05T05:24:25.174981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.07402v3","created_at":"2026-07-05T05:24:25.174981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07402","created_at":"2026-07-05T05:24:25.174981+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4ZWVYY5745A","created_at":"2026-07-05T05:24:25.174981+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4ZWVYY5745AO6XW","created_at":"2026-07-05T05:24:25.174981+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4ZWVYY5","created_at":"2026-07-05T05:24:25.174981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2210.13438","citing_title":"High Fidelity Neural Audio Compression","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4ZWVYY5745AO6XWACMWNXNHOG","json":"https://pith.science/pith/I4ZWVYY5745AO6XWACMWNXNHOG.json","graph_json":"https://pith.science/api/pith-number/I4ZWVYY5745AO6XWACMWNXNHOG/graph.json","events_json":"https://pith.science/api/pith-number/I4ZWVYY5745AO6XWACMWNXNHOG/events.json","paper":"https://pith.science/paper/I4ZWVYY5"},"agent_actions":{"view_html":"https://pith.science/pith/I4ZWVYY5745AO6XWACMWNXNHOG","download_json":"https://pith.science/pith/I4ZWVYY5745AO6XWACMWNXNHOG.json","view_paper":"https://pith.science/paper/I4ZWVYY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.07402&json=true","fetch_graph":"https://pith.science/api/pith-number/I4ZWVYY5745AO6XWACMWNXNHOG/graph.json","fetch_events":"https://pith.science/api/pith-number/I4ZWVYY5745AO6XWACMWNXNHOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4ZWVYY5745AO6XWACMWNXNHOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4ZWVYY5745AO6XWACMWNXNHOG/action/storage_attestation","attest_author":"https://pith.science/pith/I4ZWVYY5745AO6XWACMWNXNHOG/action/author_attestation","sign_citation":"https://pith.science/pith/I4ZWVYY5745AO6XWACMWNXNHOG/action/citation_signature","submit_replication":"https://pith.science/pith/I4ZWVYY5745AO6XWACMWNXNHOG/action/replication_record"}},"created_at":"2026-07-05T05:24:25.174981+00:00","updated_at":"2026-07-05T05:24:25.174981+00:00"}