{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WJANZKP4LAWSMI3YLDTG7422JD","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":"bd940e4dde87ddb83c1ce96113cf4e44b388438ccf2abd3207cc303a2ab08610","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T19:22:13Z","title_canon_sha256":"0c83ee0fadd28e293c1cc3df7948799d9a3866b7ab093a20b84df4930e236b96"},"schema_version":"1.0","source":{"id":"2406.02733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02733","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02733v1","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02733","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_12","alias_value":"WJANZKP4LAWS","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_16","alias_value":"WJANZKP4LAWSMI3Y","created_at":"2026-07-05T08:27:29Z"},{"alias_kind":"pith_short_8","alias_value":"WJANZKP4","created_at":"2026-07-05T08:27:29Z"}],"graph_snapshots":[{"event_id":"sha256:9af823077f3b0851e4b870e40e8722b2c7cc0cd4170dd3265a66bd10e03c1c71","target":"graph","created_at":"2026-07-05T08:27:29Z","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/2406.02733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a textless acoustic model with a self-supervised distillation strategy for noise-robust expressive speech-to-speech translation (S2ST). Recently proposed expressive S2ST systems have achieved impressive expressivity preservation performances by cascading unit-to-speech (U2S) generator to the speech-to-unit translation model. However, these systems are vulnerable to the presence of noise in input speech, which is an assumption in real-world translation scenarios. To address this limitation, we propose a U2S generator that incorporates a distillation with no label (DINO","authors_text":"Ann Lee, Benjamin Peloquin, Hongyu Gong, Ilia Kulikov, Min-Jae Hwang, Peng-Jen Chen","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T19:22:13Z","title":"Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02733","kind":"arxiv","version":1},"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":"sha256:9f96574539ed2b1c3b102b5dce78c651c3689eaa171ff1be0b4abc67358eb9eb","target":"record","created_at":"2026-07-05T08:27:29Z","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":"bd940e4dde87ddb83c1ce96113cf4e44b388438ccf2abd3207cc303a2ab08610","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T19:22:13Z","title_canon_sha256":"0c83ee0fadd28e293c1cc3df7948799d9a3866b7ab093a20b84df4930e236b96"},"schema_version":"1.0","source":{"id":"2406.02733","kind":"arxiv","version":1}},"canonical_sha256":"b240dca9fc582d26237858e66ff35a48feedb5b58173321f96e0d854ebd581d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b240dca9fc582d26237858e66ff35a48feedb5b58173321f96e0d854ebd581d6","first_computed_at":"2026-07-05T08:27:29.455332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:29.455332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NG0SW2ViQE62hdjfUUiDtFyOykDAjX3YU7tsQrwAFuElnD39sy3prFp0qK+rFJGiEBwkTnYtgKNBaQfYvKHNDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:29.456580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f96574539ed2b1c3b102b5dce78c651c3689eaa171ff1be0b4abc67358eb9eb","sha256:9af823077f3b0851e4b870e40e8722b2c7cc0cd4170dd3265a66bd10e03c1c71"],"state_sha256":"bf0e647ad189e6594c20290069201e5a6655ba9a8a78406a1afb5a7099352bfc"}