{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EAM5OT6SHO5HDB3S7JDA2ZGWOZ","short_pith_number":"pith:EAM5OT6S","schema_version":"1.0","canonical_sha256":"2019d74fd23bba718772fa460d64d6766d5d832e992b077e5917406640deaa84","source":{"kind":"arxiv","id":"2406.06251","version":1},"attestation_state":"computed","paper":{"title":"Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Andros Tjandra, Apoorv Vyas, Bowen Shi, Chung-Ming Chien, Matt Le, Wei-Ning Hsu","submitted_at":"2024-06-10T13:31:18Z","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"},"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":"2406.06251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-10T13:31:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9abe698f0615ec17b36847d7e567ed7e0eeb850f47f1e6d320077743b4cf565e","abstract_canon_sha256":"dc171d5465ecf3307fba03f1bb4e860ff7507c524d014019366e15b01d137d52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:39.800848Z","signature_b64":"Fovxp8EdeExsVaUd+r962hr/5O03JVr107fI8nyXNXX4mA5/BDQ7SrNt3EPis6MWQut2L3bEt1hmpBIK94UTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2019d74fd23bba718772fa460d64d6766d5d832e992b077e5917406640deaa84","last_reissued_at":"2026-07-05T08:29:39.800433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:39.800433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Andros Tjandra, Apoorv Vyas, Bowen Shi, Chung-Ming Chien, Matt Le, Wei-Ning Hsu","submitted_at":"2024-06-10T13:31:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06251","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/2406.06251/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":"2406.06251","created_at":"2026-07-05T08:29:39.800489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06251v1","created_at":"2026-07-05T08:29:39.800489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06251","created_at":"2026-07-05T08:29:39.800489+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAM5OT6SHO5H","created_at":"2026-07-05T08:29:39.800489+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAM5OT6SHO5HDB3S","created_at":"2026-07-05T08:29:39.800489+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAM5OT6S","created_at":"2026-07-05T08:29:39.800489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07562","citing_title":"LoRP-TTS: Low-Rank Personalized Text-To-Speech","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EAM5OT6SHO5HDB3S7JDA2ZGWOZ","json":"https://pith.science/pith/EAM5OT6SHO5HDB3S7JDA2ZGWOZ.json","graph_json":"https://pith.science/api/pith-number/EAM5OT6SHO5HDB3S7JDA2ZGWOZ/graph.json","events_json":"https://pith.science/api/pith-number/EAM5OT6SHO5HDB3S7JDA2ZGWOZ/events.json","paper":"https://pith.science/paper/EAM5OT6S"},"agent_actions":{"view_html":"https://pith.science/pith/EAM5OT6SHO5HDB3S7JDA2ZGWOZ","download_json":"https://pith.science/pith/EAM5OT6SHO5HDB3S7JDA2ZGWOZ.json","view_paper":"https://pith.science/paper/EAM5OT6S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06251&json=true","fetch_graph":"https://pith.science/api/pith-number/EAM5OT6SHO5HDB3S7JDA2ZGWOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/EAM5OT6SHO5HDB3S7JDA2ZGWOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAM5OT6SHO5HDB3S7JDA2ZGWOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAM5OT6SHO5HDB3S7JDA2ZGWOZ/action/storage_attestation","attest_author":"https://pith.science/pith/EAM5OT6SHO5HDB3S7JDA2ZGWOZ/action/author_attestation","sign_citation":"https://pith.science/pith/EAM5OT6SHO5HDB3S7JDA2ZGWOZ/action/citation_signature","submit_replication":"https://pith.science/pith/EAM5OT6SHO5HDB3S7JDA2ZGWOZ/action/replication_record"}},"created_at":"2026-07-05T08:29:39.800489+00:00","updated_at":"2026-07-05T08:29:39.800489+00:00"}