{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WJANZKP4LAWSMI3YLDTG7422JD","short_pith_number":"pith:WJANZKP4","schema_version":"1.0","canonical_sha256":"b240dca9fc582d26237858e66ff35a48feedb5b58173321f96e0d854ebd581d6","source":{"kind":"arxiv","id":"2406.02733","version":1},"attestation_state":"computed","paper":{"title":"Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ann Lee, Benjamin Peloquin, Hongyu Gong, Ilia Kulikov, Min-Jae Hwang, Peng-Jen Chen","submitted_at":"2024-06-04T19:22:13Z","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"},"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":"2406.02733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T19:22:13Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0c83ee0fadd28e293c1cc3df7948799d9a3866b7ab093a20b84df4930e236b96","abstract_canon_sha256":"bd940e4dde87ddb83c1ce96113cf4e44b388438ccf2abd3207cc303a2ab08610"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:29.456580Z","signature_b64":"NG0SW2ViQE62hdjfUUiDtFyOykDAjX3YU7tsQrwAFuElnD39sy3prFp0qK+rFJGiEBwkTnYtgKNBaQfYvKHNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b240dca9fc582d26237858e66ff35a48feedb5b58173321f96e0d854ebd581d6","last_reissued_at":"2026-07-05T08:27:29.455332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:29.455332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ann Lee, Benjamin Peloquin, Hongyu Gong, Ilia Kulikov, Min-Jae Hwang, Peng-Jen Chen","submitted_at":"2024-06-04T19:22:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02733","kind":"arxiv","version":1},"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/2406.02733/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":"2406.02733","created_at":"2026-07-05T08:27:29.455983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02733v1","created_at":"2026-07-05T08:27:29.455983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02733","created_at":"2026-07-05T08:27:29.455983+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJANZKP4LAWS","created_at":"2026-07-05T08:27:29.455983+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJANZKP4LAWSMI3Y","created_at":"2026-07-05T08:27:29.455983+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJANZKP4","created_at":"2026-07-05T08:27:29.455983+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/WJANZKP4LAWSMI3YLDTG7422JD","json":"https://pith.science/pith/WJANZKP4LAWSMI3YLDTG7422JD.json","graph_json":"https://pith.science/api/pith-number/WJANZKP4LAWSMI3YLDTG7422JD/graph.json","events_json":"https://pith.science/api/pith-number/WJANZKP4LAWSMI3YLDTG7422JD/events.json","paper":"https://pith.science/paper/WJANZKP4"},"agent_actions":{"view_html":"https://pith.science/pith/WJANZKP4LAWSMI3YLDTG7422JD","download_json":"https://pith.science/pith/WJANZKP4LAWSMI3YLDTG7422JD.json","view_paper":"https://pith.science/paper/WJANZKP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02733&json=true","fetch_graph":"https://pith.science/api/pith-number/WJANZKP4LAWSMI3YLDTG7422JD/graph.json","fetch_events":"https://pith.science/api/pith-number/WJANZKP4LAWSMI3YLDTG7422JD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJANZKP4LAWSMI3YLDTG7422JD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJANZKP4LAWSMI3YLDTG7422JD/action/storage_attestation","attest_author":"https://pith.science/pith/WJANZKP4LAWSMI3YLDTG7422JD/action/author_attestation","sign_citation":"https://pith.science/pith/WJANZKP4LAWSMI3YLDTG7422JD/action/citation_signature","submit_replication":"https://pith.science/pith/WJANZKP4LAWSMI3YLDTG7422JD/action/replication_record"}},"created_at":"2026-07-05T08:27:29.455983+00:00","updated_at":"2026-07-05T08:27:29.455983+00:00"}