{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MDSIZTJPFN4ON7HW5HEUNDWHYZ","short_pith_number":"pith:MDSIZTJP","schema_version":"1.0","canonical_sha256":"60e48ccd2f2b78e6fcf6e9c9468ec7c666d6e9449c3735c6239b2f2710509528","source":{"kind":"arxiv","id":"2409.06666","version":2},"attestation_state":"computed","paper":{"title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Qingkai Fang, Shaolei Zhang, Shoutao Guo, Yang Feng, Yan Zhou, Zhengrui Ma","submitted_at":"2024-09-10T17:34:34Z","abstract_excerpt":"Models like GPT-4o enable real-time interaction with large language models (LLMs) through speech, significantly enhancing user experience compared to traditional text-based interaction. However, there is still a lack of exploration on how to build speech interaction models based on open-source LLMs. To address this, we propose LLaMA-Omni, a novel model architecture designed for low-latency and high-quality speech interaction with LLMs. LLaMA-Omni integrates a pretrained speech encoder, a speech adaptor, an LLM, and a streaming speech decoder. It eliminates the need for speech transcription, an"},"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":"2409.06666","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-10T17:34:34Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"7aa3dde4cb554c04e0b2c9377c3769a5a4d950348592f57f42a56143d900fb51","abstract_canon_sha256":"ed8da009c68bc81978b8447384d9cd5979a4a4fe14306e1551e5801aaea3387f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:04.358204Z","signature_b64":"83y7PwsUb+ZFmOPOIaLltLRd167ZUujz3cRElr4uqvogBuz1gF0unmLCkhPyqsmo2Xkne0nevYbIYjYuhy+GDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60e48ccd2f2b78e6fcf6e9c9468ec7c666d6e9449c3735c6239b2f2710509528","last_reissued_at":"2026-07-05T10:22:04.357619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:04.357619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLaMA-Omni: Seamless Speech Interaction with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Qingkai Fang, Shaolei Zhang, Shoutao Guo, Yang Feng, Yan Zhou, Zhengrui Ma","submitted_at":"2024-09-10T17:34:34Z","abstract_excerpt":"Models like GPT-4o enable real-time interaction with large language models (LLMs) through speech, significantly enhancing user experience compared to traditional text-based interaction. However, there is still a lack of exploration on how to build speech interaction models based on open-source LLMs. To address this, we propose LLaMA-Omni, a novel model architecture designed for low-latency and high-quality speech interaction with LLMs. LLaMA-Omni integrates a pretrained speech encoder, a speech adaptor, an LLM, and a streaming speech decoder. It eliminates the need for speech transcription, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06666","kind":"arxiv","version":2},"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/2409.06666/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":"2409.06666","created_at":"2026-07-05T10:22:04.357688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06666v2","created_at":"2026-07-05T10:22:04.357688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06666","created_at":"2026-07-05T10:22:04.357688+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDSIZTJPFN4O","created_at":"2026-07-05T10:22:04.357688+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDSIZTJPFN4ON7HW","created_at":"2026-07-05T10:22:04.357688+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDSIZTJP","created_at":"2026-07-05T10:22:04.357688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21882","citing_title":"Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12199","citing_title":"Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11400","citing_title":"Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05121","citing_title":"Audio Interaction Model","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31294","citing_title":"TokTalk: Expressive Real-time Facial Animation from Audio-LLM Tokens","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":215,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03526","citing_title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21008","citing_title":"A Survey of Audio Reasoning in Multimodal Foundation Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2502.11946","citing_title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22220","citing_title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2501.01957","citing_title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2410.17196","citing_title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02612","citing_title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22710","citing_title":"Same Words, Different Judgments: How Preferences Vary Across Modalities","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05927","citing_title":"Minimizing Modality Gap from the Input Side: Your Speech LLM Can Be a Prosody-Aware Text LLM","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18425","citing_title":"Kimi-Audio Technical Report","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03937","citing_title":"MiniMind-O Technical Report: An Open Small-Scale Speech-Native Omni Model","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06765","citing_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ","json":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ.json","graph_json":"https://pith.science/api/pith-number/MDSIZTJPFN4ON7HW5HEUNDWHYZ/graph.json","events_json":"https://pith.science/api/pith-number/MDSIZTJPFN4ON7HW5HEUNDWHYZ/events.json","paper":"https://pith.science/paper/MDSIZTJP"},"agent_actions":{"view_html":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ","download_json":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ.json","view_paper":"https://pith.science/paper/MDSIZTJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06666&json=true","fetch_graph":"https://pith.science/api/pith-number/MDSIZTJPFN4ON7HW5HEUNDWHYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MDSIZTJPFN4ON7HW5HEUNDWHYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/action/storage_attestation","attest_author":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/action/author_attestation","sign_citation":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/action/citation_signature","submit_replication":"https://pith.science/pith/MDSIZTJPFN4ON7HW5HEUNDWHYZ/action/replication_record"}},"created_at":"2026-07-05T10:22:04.357688+00:00","updated_at":"2026-07-05T10:22:04.357688+00:00"}