{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4ULKVTBSD5FZPWHHS2PI3HGJLL","short_pith_number":"pith:4ULKVTBS","schema_version":"1.0","canonical_sha256":"e516aacc321f4b97d8e7969e8d9cc95acd3a46bb31e65a6f332a91d8498892d2","source":{"kind":"arxiv","id":"2305.11000","version":2},"attestation_state":"computed","paper":{"title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Zhang, Jun Zhan, Pengyu Wang, Shimin Li, Xin Zhang, Xipeng Qiu, Yaqian Zhou","submitted_at":"2023-05-18T14:23:25Z","abstract_excerpt":"Multi-modal large language models are regarded as a crucial step towards Artificial General Intelligence (AGI) and have garnered significant interest with the emergence of ChatGPT. However, current speech-language models typically adopt the cascade paradigm, preventing inter-modal knowledge transfer. In this paper, we propose SpeechGPT, a large language model with intrinsic cross-modal conversational abilities, capable of perceiving and generating multi-model content. With discrete speech representations, we first construct SpeechInstruct, a large-scale cross-modal speech instruction dataset. "},"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":"2305.11000","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T14:23:25Z","cross_cats_sorted":[],"title_canon_sha256":"e72cb6e1dedcbe796f99c1cf12c1199865b6c0a29de6162303dd7273b5d44fba","abstract_canon_sha256":"6164e2c792484793ace88d3435b9552649525d230c850dc5da73623ecd436cb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:46.417189Z","signature_b64":"Yul18DKrHukgpCc1J8a1mC2Ua8jd9RbyDk8cVOMpUBBDi8rguHRqtKmyAhmfzHaO20PMz66Z+G0gXpH4EhM/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e516aacc321f4b97d8e7969e8d9cc95acd3a46bb31e65a6f332a91d8498892d2","last_reissued_at":"2026-07-05T06:11:46.416771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:46.416771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Zhang, Jun Zhan, Pengyu Wang, Shimin Li, Xin Zhang, Xipeng Qiu, Yaqian Zhou","submitted_at":"2023-05-18T14:23:25Z","abstract_excerpt":"Multi-modal large language models are regarded as a crucial step towards Artificial General Intelligence (AGI) and have garnered significant interest with the emergence of ChatGPT. However, current speech-language models typically adopt the cascade paradigm, preventing inter-modal knowledge transfer. In this paper, we propose SpeechGPT, a large language model with intrinsic cross-modal conversational abilities, capable of perceiving and generating multi-model content. With discrete speech representations, we first construct SpeechInstruct, a large-scale cross-modal speech instruction dataset. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11000","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/2305.11000/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":"2305.11000","created_at":"2026-07-05T06:11:46.416826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11000v2","created_at":"2026-07-05T06:11:46.416826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11000","created_at":"2026-07-05T06:11:46.416826+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ULKVTBSD5FZ","created_at":"2026-07-05T06:11:46.416826+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ULKVTBSD5FZPWHH","created_at":"2026-07-05T06:11:46.416826+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ULKVTBS","created_at":"2026-07-05T06:11:46.416826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25444","citing_title":"Does Translation-Enhanced Speech Encoder Pre-training Affect Speech LLMs?","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21147","citing_title":"AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?","ref_index":27,"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":12,"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":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01802","citing_title":"MOSS-Audio Technical Report","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01677","citing_title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07643","citing_title":"AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28642","citing_title":"Bandwidth-Efficient and Privacy-Preserving Edge-Cloud Many-to-Many Speech Translation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27627","citing_title":"HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00851","citing_title":"Sympatheia: Emotionally Adaptive Voice Assistant with Continuous Affect Conditioning","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":59,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01537","citing_title":"Two-Dimensional Quantization for Geometry-Aware Audio Coding","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20946","citing_title":"Thinking-while-speaking: A Controlled, Interleaved Reasoning Method for Real-Time Speech Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16026","citing_title":"From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19101","citing_title":"Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2310.13289","citing_title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01101","citing_title":"TSVer: A Benchmark for Fact Verification Against Time-Series Evidence","ref_index":55,"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":13,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01512","citing_title":"MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.02231","citing_title":"See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":82,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":205,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15045","citing_title":"LLMs and Speech: Integration vs. Combination","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ULKVTBSD5FZPWHHS2PI3HGJLL","json":"https://pith.science/pith/4ULKVTBSD5FZPWHHS2PI3HGJLL.json","graph_json":"https://pith.science/api/pith-number/4ULKVTBSD5FZPWHHS2PI3HGJLL/graph.json","events_json":"https://pith.science/api/pith-number/4ULKVTBSD5FZPWHHS2PI3HGJLL/events.json","paper":"https://pith.science/paper/4ULKVTBS"},"agent_actions":{"view_html":"https://pith.science/pith/4ULKVTBSD5FZPWHHS2PI3HGJLL","download_json":"https://pith.science/pith/4ULKVTBSD5FZPWHHS2PI3HGJLL.json","view_paper":"https://pith.science/paper/4ULKVTBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11000&json=true","fetch_graph":"https://pith.science/api/pith-number/4ULKVTBSD5FZPWHHS2PI3HGJLL/graph.json","fetch_events":"https://pith.science/api/pith-number/4ULKVTBSD5FZPWHHS2PI3HGJLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ULKVTBSD5FZPWHHS2PI3HGJLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ULKVTBSD5FZPWHHS2PI3HGJLL/action/storage_attestation","attest_author":"https://pith.science/pith/4ULKVTBSD5FZPWHHS2PI3HGJLL/action/author_attestation","sign_citation":"https://pith.science/pith/4ULKVTBSD5FZPWHHS2PI3HGJLL/action/citation_signature","submit_replication":"https://pith.science/pith/4ULKVTBSD5FZPWHHS2PI3HGJLL/action/replication_record"}},"created_at":"2026-07-05T06:11:46.416826+00:00","updated_at":"2026-07-05T06:11:46.416826+00:00"}