{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TRUCNY7T32ENQ5KZMSTR4ZK4PR","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":"9b4a620dda0fe1737e53d7290979c87f602123dadc7a797c8f14ecf2a15f143a","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-27T04:28:57Z","title_canon_sha256":"c22f0a6dd6f9ee5b02ff1285a1b167ee7d5dac6ee25e043b07fc7d8f2e20aae7"},"schema_version":"1.0","source":{"id":"2410.20336","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20336","created_at":"2026-07-05T09:26:43Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20336v1","created_at":"2026-07-05T09:26:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20336","created_at":"2026-07-05T09:26:43Z"},{"alias_kind":"pith_short_12","alias_value":"TRUCNY7T32EN","created_at":"2026-07-05T09:26:43Z"},{"alias_kind":"pith_short_16","alias_value":"TRUCNY7T32ENQ5KZ","created_at":"2026-07-05T09:26:43Z"},{"alias_kind":"pith_short_8","alias_value":"TRUCNY7T","created_at":"2026-07-05T09:26:43Z"}],"graph_snapshots":[{"event_id":"sha256:cec4cae543f26963d3b27db890b85dad72322cae2eb26835e6c0503caeb4dbfa","target":"graph","created_at":"2026-07-05T09:26:43Z","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/2410.20336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing (NLP) with impressive performance across various text-based tasks. However, the extension of text-dominant LLMs to with speech generation tasks remains under-explored. In this work, we introduce a text-to-speech (TTS) system powered by a fine-tuned Llama model, named TTS-Llama, that achieves state-of-the-art speech synthesis performance. Building on TTS-Llama, we further propose MoLE-Llama, a text-and-speech multimodal LLM developed through purely late-fusion parameter-efficient fine-tuning (PEFT) and a mixture-of-exp","authors_text":"Ehab AlBadawy, Jilong Wu, Maohao Shen, Mike Seltzer, Qing He, Shun Zhang, Yiting Lu, Zhiping Xiu","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-27T04:28:57Z","title":"Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20336","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":"sha256:3fbd8483b6a83e214bc11f4c7c42aedcda75752425ac6919cd3cd1e9f13458c3","target":"record","created_at":"2026-07-05T09:26:43Z","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":"9b4a620dda0fe1737e53d7290979c87f602123dadc7a797c8f14ecf2a15f143a","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-27T04:28:57Z","title_canon_sha256":"c22f0a6dd6f9ee5b02ff1285a1b167ee7d5dac6ee25e043b07fc7d8f2e20aae7"},"schema_version":"1.0","source":{"id":"2410.20336","kind":"arxiv","version":1}},"canonical_sha256":"9c6826e3f3de88d8755964a71e655c7c45174a7318c1e967f736e296bf6ed163","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c6826e3f3de88d8755964a71e655c7c45174a7318c1e967f736e296bf6ed163","first_computed_at":"2026-07-05T09:26:43.377926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:43.377926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PNpANwl0nIbh4elG2ZjUSO4+8OskXExW9A6UUzY6VCenW5aovbFecuZZDP2Q2fBZI4BKckrZ3iH4vYHfsIPmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:43.378402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20336","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fbd8483b6a83e214bc11f4c7c42aedcda75752425ac6919cd3cd1e9f13458c3","sha256:cec4cae543f26963d3b27db890b85dad72322cae2eb26835e6c0503caeb4dbfa"],"state_sha256":"59b6b7e1aa064e841ce46258ee998573f05ec450ab8ced5b7243e5e0d5869413"}