{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7XOWG4QH4V3OFWKQUJZC63UQCZ","short_pith_number":"pith:7XOWG4QH","schema_version":"1.0","canonical_sha256":"fddd637207e576e2d950a2722f6e9016556fec5f2282484a43fcee85a683f2eb","source":{"kind":"arxiv","id":"2411.00774","version":5},"attestation_state":"computed","paper":{"title":"Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaoyou Fu, Ke Li, Lei Xie, Long Ma, Xing Sun, Xiong Wang, Yangze Li, Yunhang Shen","submitted_at":"2024-11-01T17:59:51Z","abstract_excerpt":"Rapidly developing large language models (LLMs) have brought tremendous intelligent applications. Especially, the GPT-4o's excellent duplex speech interaction ability has brought impressive experience to users. Researchers have recently proposed several multi-modal LLMs in this direction that can achieve user-agent speech-to-speech conversations. This paper proposes a novel speech-text multimodal LLM architecture called Freeze-Omni. Our main contribution is that the speech input and output modalities can be easily connected to a textual LLM while keeping the LLM's parameters frozen throughout "},"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":"2411.00774","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-11-01T17:59:51Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"26d81c0e33aa21e498e22ea2144e71c18dbf28dc4c6d2cb1340045255c5ed51a","abstract_canon_sha256":"cbeb8fe77d91ea7748ccea21d53035a5b4b76d0ae1c4849256511aeeb3c97edc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:57.069550Z","signature_b64":"zHT4DWXr+wlfnuIxX264KACViKCL+nSioiHaEFchyjr047ECflch/OK1FbOkhgS9aDY0whsgBrayqATJMFUXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fddd637207e576e2d950a2722f6e9016556fec5f2282484a43fcee85a683f2eb","last_reissued_at":"2026-07-05T09:45:57.068979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:57.068979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chaoyou Fu, Ke Li, Lei Xie, Long Ma, Xing Sun, Xiong Wang, Yangze Li, Yunhang Shen","submitted_at":"2024-11-01T17:59:51Z","abstract_excerpt":"Rapidly developing large language models (LLMs) have brought tremendous intelligent applications. Especially, the GPT-4o's excellent duplex speech interaction ability has brought impressive experience to users. Researchers have recently proposed several multi-modal LLMs in this direction that can achieve user-agent speech-to-speech conversations. This paper proposes a novel speech-text multimodal LLM architecture called Freeze-Omni. Our main contribution is that the speech input and output modalities can be easily connected to a textual LLM while keeping the LLM's parameters frozen throughout "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00774","kind":"arxiv","version":5},"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/2411.00774/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":"2411.00774","created_at":"2026-07-05T09:45:57.069048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00774v5","created_at":"2026-07-05T09:45:57.069048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00774","created_at":"2026-07-05T09:45:57.069048+00:00"},{"alias_kind":"pith_short_12","alias_value":"7XOWG4QH4V3O","created_at":"2026-07-05T09:45:57.069048+00:00"},{"alias_kind":"pith_short_16","alias_value":"7XOWG4QH4V3OFWKQ","created_at":"2026-07-05T09:45:57.069048+00:00"},{"alias_kind":"pith_short_8","alias_value":"7XOWG4QH","created_at":"2026-07-05T09:45:57.069048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":29,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19453","citing_title":"A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State Machine","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13544","citing_title":"Adaptive Turn-Taking for Real-time Multi-Party Voice Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02214","citing_title":"Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning","ref_index":28,"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":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06559","citing_title":"IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spoken Dialogue Systems","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05121","citing_title":"Audio Interaction Model","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30944","citing_title":"Preserving Speech-to-Text LLM Capabilities in Speech-to-Speech Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":216,"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":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30145","citing_title":"FacePlex: Full-Duplex Joint Speech-Facial Motion Generation for Conversational Avatars","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13544","citing_title":"Adaptive Turn-Taking for Real-time Multi-Party Voice Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27190","citing_title":"Learning When to Think While Listening in Large Audio-Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14654","citing_title":"Beyond Words: Multimodal LLM Knows When to Speak","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20266","citing_title":"A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook","ref_index":123,"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":4,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14804","citing_title":"Towards Building Speech Large Language Models for Multitask Understanding in Low-Resource Languages","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2502.11946","citing_title":"Step-Audio: Unified Understanding and Generation in Intelligent Speech Interaction","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22220","citing_title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","ref_index":74,"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":40,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":67,"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":42,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ","json":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ.json","graph_json":"https://pith.science/api/pith-number/7XOWG4QH4V3OFWKQUJZC63UQCZ/graph.json","events_json":"https://pith.science/api/pith-number/7XOWG4QH4V3OFWKQUJZC63UQCZ/events.json","paper":"https://pith.science/paper/7XOWG4QH"},"agent_actions":{"view_html":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ","download_json":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ.json","view_paper":"https://pith.science/paper/7XOWG4QH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00774&json=true","fetch_graph":"https://pith.science/api/pith-number/7XOWG4QH4V3OFWKQUJZC63UQCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7XOWG4QH4V3OFWKQUJZC63UQCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/action/storage_attestation","attest_author":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/action/author_attestation","sign_citation":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/action/citation_signature","submit_replication":"https://pith.science/pith/7XOWG4QH4V3OFWKQUJZC63UQCZ/action/replication_record"}},"created_at":"2026-07-05T09:45:57.069048+00:00","updated_at":"2026-07-05T09:45:57.069048+00:00"}