{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TRDEPHGEJUBEM35KU4MIQM2WKJ","short_pith_number":"pith:TRDEPHGE","schema_version":"1.0","canonical_sha256":"9c46479cc44d02466faaa718883356526c4d3580d82fa36fc8d02f46f7b58440","source":{"kind":"arxiv","id":"2606.07240","version":1},"attestation_state":"computed","paper":{"title":"KIT's Submission to Cross-Lingual Voice Cloning in IWSLT 2026","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CL","authors_text":"Alexander Waibel, Seymanur Akti","submitted_at":"2026-06-05T13:09:21Z","abstract_excerpt":"Cross-lingual voice cloning aims to generate speech in a target language while preserving speaker identity from a source-language reference. This task is central to speech translation and is the focus of the IWSLT 2026 Cross-Lingual Voice Cloning track. A key challenge is maintaining intelligibility and naturalness in the presence of accent variation and domain-specific vocabulary. We build on a multilingual text-to-speech model, FishAudio-S2-Pro, and introduce language tag prompting to improve language control and reduce accent leakage. We further apply reinforcement learning (RL) fine-tuning"},"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":"2606.07240","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T13:09:21Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"126658051899100d523ff49a9a4c00574a3cdb8b48186e21dda5df9de534d248","abstract_canon_sha256":"e08dd8762becbef989c36d753d2227524edb6d3fe475dab2c2eb4314b3df27af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:14.913648Z","signature_b64":"L9e2Q6c614dsvJjP1ozfUEKzAefZm6PrRRamrJ4wmZNbXHYztuFbI77MmwOF6SmLAE+YiOOGnuOEnf21/CcBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c46479cc44d02466faaa718883356526c4d3580d82fa36fc8d02f46f7b58440","last_reissued_at":"2026-06-08T01:05:14.912749Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:14.912749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KIT's Submission to Cross-Lingual Voice Cloning in IWSLT 2026","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CL","authors_text":"Alexander Waibel, Seymanur Akti","submitted_at":"2026-06-05T13:09:21Z","abstract_excerpt":"Cross-lingual voice cloning aims to generate speech in a target language while preserving speaker identity from a source-language reference. This task is central to speech translation and is the focus of the IWSLT 2026 Cross-Lingual Voice Cloning track. A key challenge is maintaining intelligibility and naturalness in the presence of accent variation and domain-specific vocabulary. We build on a multilingual text-to-speech model, FishAudio-S2-Pro, and introduce language tag prompting to improve language control and reduce accent leakage. We further apply reinforcement learning (RL) fine-tuning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07240","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/2606.07240/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":"2606.07240","created_at":"2026-06-08T01:05:14.912897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07240v1","created_at":"2026-06-08T01:05:14.912897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07240","created_at":"2026-06-08T01:05:14.912897+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRDEPHGEJUBE","created_at":"2026-06-08T01:05:14.912897+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRDEPHGEJUBEM35K","created_at":"2026-06-08T01:05:14.912897+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRDEPHGE","created_at":"2026-06-08T01:05:14.912897+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/TRDEPHGEJUBEM35KU4MIQM2WKJ","json":"https://pith.science/pith/TRDEPHGEJUBEM35KU4MIQM2WKJ.json","graph_json":"https://pith.science/api/pith-number/TRDEPHGEJUBEM35KU4MIQM2WKJ/graph.json","events_json":"https://pith.science/api/pith-number/TRDEPHGEJUBEM35KU4MIQM2WKJ/events.json","paper":"https://pith.science/paper/TRDEPHGE"},"agent_actions":{"view_html":"https://pith.science/pith/TRDEPHGEJUBEM35KU4MIQM2WKJ","download_json":"https://pith.science/pith/TRDEPHGEJUBEM35KU4MIQM2WKJ.json","view_paper":"https://pith.science/paper/TRDEPHGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07240&json=true","fetch_graph":"https://pith.science/api/pith-number/TRDEPHGEJUBEM35KU4MIQM2WKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TRDEPHGEJUBEM35KU4MIQM2WKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRDEPHGEJUBEM35KU4MIQM2WKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRDEPHGEJUBEM35KU4MIQM2WKJ/action/storage_attestation","attest_author":"https://pith.science/pith/TRDEPHGEJUBEM35KU4MIQM2WKJ/action/author_attestation","sign_citation":"https://pith.science/pith/TRDEPHGEJUBEM35KU4MIQM2WKJ/action/citation_signature","submit_replication":"https://pith.science/pith/TRDEPHGEJUBEM35KU4MIQM2WKJ/action/replication_record"}},"created_at":"2026-06-08T01:05:14.912897+00:00","updated_at":"2026-06-08T01:05:14.912897+00:00"}