{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EAM5OT6SHO5HDB3S7JDA2ZGWOZ","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":"dc171d5465ecf3307fba03f1bb4e860ff7507c524d014019366e15b01d137d52","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-10T13:31:18Z","title_canon_sha256":"9abe698f0615ec17b36847d7e567ed7e0eeb850f47f1e6d320077743b4cf565e"},"schema_version":"1.0","source":{"id":"2406.06251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06251","created_at":"2026-07-05T08:29:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06251v1","created_at":"2026-07-05T08:29:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06251","created_at":"2026-07-05T08:29:39Z"},{"alias_kind":"pith_short_12","alias_value":"EAM5OT6SHO5H","created_at":"2026-07-05T08:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"EAM5OT6SHO5HDB3S","created_at":"2026-07-05T08:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"EAM5OT6S","created_at":"2026-07-05T08:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:bd8c6f267fd04e9e3056f5208f7ef9cc39541f20d9f54493f00f5f3a0544cefe","target":"graph","created_at":"2026-07-05T08:29:39Z","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/2406.06251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the scale of generative models continues to grow, efficient reuse and adaptation of pre-trained models have become crucial considerations. In this work, we propose Voicebox Adapter, a novel approach that integrates fine-grained conditions into a pre-trained Voicebox speech generation model using a cross-attention module. To ensure a smooth integration of newly added modules with pre-trained ones, we explore various efficient fine-tuning approaches. Our experiment shows that the LoRA with bias-tuning configuration yields the best performance, enhancing controllability without compromising sp","authors_text":"Andros Tjandra, Apoorv Vyas, Bowen Shi, Chung-Ming Chien, Matt Le, Wei-Ning Hsu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-10T13:31:18Z","title":"Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06251","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:a4f536f47df66af847ccf2f85f467751c361011e86088aaaddceb3701b31412d","target":"record","created_at":"2026-07-05T08:29:39Z","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":"dc171d5465ecf3307fba03f1bb4e860ff7507c524d014019366e15b01d137d52","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-10T13:31:18Z","title_canon_sha256":"9abe698f0615ec17b36847d7e567ed7e0eeb850f47f1e6d320077743b4cf565e"},"schema_version":"1.0","source":{"id":"2406.06251","kind":"arxiv","version":1}},"canonical_sha256":"2019d74fd23bba718772fa460d64d6766d5d832e992b077e5917406640deaa84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2019d74fd23bba718772fa460d64d6766d5d832e992b077e5917406640deaa84","first_computed_at":"2026-07-05T08:29:39.800433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:39.800433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fovxp8EdeExsVaUd+r962hr/5O03JVr107fI8nyXNXX4mA5/BDQ7SrNt3EPis6MWQut2L3bEt1hmpBIK94UTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:39.800848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4f536f47df66af847ccf2f85f467751c361011e86088aaaddceb3701b31412d","sha256:bd8c6f267fd04e9e3056f5208f7ef9cc39541f20d9f54493f00f5f3a0544cefe"],"state_sha256":"53a6e201ac8d97163bef2fc98daf6320558a0b5d742a77d7c8ffdcd788980ace"}