{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XDRDHMN3T3SQAVSFP2ZCKABITF","short_pith_number":"pith:XDRDHMN3","schema_version":"1.0","canonical_sha256":"b8e233b1bb9ee50056457eb22500289973b4161e537385c49cc64f207385d600","source":{"kind":"arxiv","id":"2410.17196","version":3},"attestation_state":"computed","paper":{"title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"VoiceBench introduces the first benchmark to evaluate LLM-based voice assistants under real-world variations in speakers, environments, and content.","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Haizhou Li, Robby T. Tan, Xianghu Yue, Xiaoxue Gao, Yiming Chen","submitted_at":"2024-10-22T17:15:20Z","abstract_excerpt":"Building on the success of large language models (LLMs), recent advancements such as GPT-4o have enabled real-time speech interactions through LLM-based voice assistants, offering a significantly improved user experience compared to traditional text-based interactions. However, the absence of benchmarks designed to evaluate these speech interaction capabilities has hindered progress of LLM-based voice assistants development. Current evaluations focus primarily on automatic speech recognition (ASR) or general knowledge evaluation with clean speeches, neglecting the more intricate, real-world sc"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2410.17196","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-22T17:15:20Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"89cc10e5f8b173057e5fbfa94b77714278acfadf0e45951cd819b631a771ec77","abstract_canon_sha256":"30a1817c039a304e979ed3fd0961d078c6c729215c13cc633a1639054246f41c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:46.069540Z","signature_b64":"PwBJYzR0knHu/L0pbaosw59UY6g9/02srse6t6K+LKLzaPcTy7OFmHI+2Kk6PhbAlqEAsk/69bqRayB2hrUwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8e233b1bb9ee50056457eb22500289973b4161e537385c49cc64f207385d600","last_reissued_at":"2026-05-17T23:38:46.069024Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:46.069024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"VoiceBench introduces the first benchmark to evaluate LLM-based voice assistants under real-world variations in speakers, environments, and content.","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Haizhou Li, Robby T. Tan, Xianghu Yue, Xiaoxue Gao, Yiming Chen","submitted_at":"2024-10-22T17:15:20Z","abstract_excerpt":"Building on the success of large language models (LLMs), recent advancements such as GPT-4o have enabled real-time speech interactions through LLM-based voice assistants, offering a significantly improved user experience compared to traditional text-based interactions. However, the absence of benchmarks designed to evaluate these speech interaction capabilities has hindered progress of LLM-based voice assistants development. Current evaluations focus primarily on automatic speech recognition (ASR) or general knowledge evaluation with clean speeches, neglecting the more intricate, real-world sc"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce VoiceBench, the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants. VoiceBench also includes both real and synthetic spoken instructions that incorporate the above three key real-world variations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the selected variations in speaker characteristics, environmental factors, and content factors adequately represent the intricate real-world scenarios that current evaluations neglect.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VoiceBench is the first benchmark for multi-faceted evaluation of LLM voice assistants using real and synthetic spoken instructions with speaker, environmental, and content variations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"VoiceBench introduces the first benchmark to evaluate LLM-based voice assistants under real-world variations in speakers, environments, and content.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"da6901dd0f53cc640dfd4246ea233c47861fa79648cff946c80bf53476223f48"},"source":{"id":"2410.17196","kind":"arxiv","version":3},"verdict":{"id":"b4739c94-417f-4410-b0da-3ccddff6302c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T00:44:53.168044Z","strongest_claim":"We introduce VoiceBench, the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants. VoiceBench also includes both real and synthetic spoken instructions that incorporate the above three key real-world variations.","one_line_summary":"VoiceBench is the first benchmark for multi-faceted evaluation of LLM voice assistants using real and synthetic spoken instructions with speaker, environmental, and content variations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the selected variations in speaker characteristics, environmental factors, and content factors adequately represent the intricate real-world scenarios that current evaluations neglect.","pith_extraction_headline":"VoiceBench introduces the first benchmark to evaluate LLM-based voice assistants under real-world variations in speakers, environments, and content."},"references":{"count":85,"sample":[{"doi":"","year":null,"title":"Advances in Neural Information Processing Systems , volume=","work_id":"35076cd8-2723-4c99-b604-65676abad5b8","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Twelfth International Conference on Learning Representations , year=","work_id":"324853f3-6bd4-422b-b68c-2ed4fc1e0394","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The Twelfth International Conference on Learning Representations , year=","work_id":"13d914fb-8f91-4a50-9c77-40b04fba8d96","ref_index":7,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1994,"title":"Preliminaries to a theory of speech disfluencies , author=. 1994 , school=","work_id":"9fb6096f-3706-4752-a22c-c88c6778e55e","ref_index":13,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Advances in neural information processing systems , volume=","work_id":"f2a4f68e-48af-40c6-90d4-76b155136aa5","ref_index":14,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":85,"snapshot_sha256":"d21bca70ec65b4bc4c5adcb504e06df5c8abbede9c390bf6f474d5ca6c2b74bb","internal_anchors":10},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5efe2de4480e92fb74930c7f438726b937bd90861ca54708e829342465816f4e"},"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":"2410.17196","created_at":"2026-05-17T23:38:46.069112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17196v3","created_at":"2026-05-17T23:38:46.069112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17196","created_at":"2026-05-17T23:38:46.069112+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDRDHMN3T3SQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDRDHMN3T3SQAVSF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDRDHMN3","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":20,"sample":[{"citing_arxiv_id":"2509.23435","citing_title":"AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2509.26388","citing_title":"Game-Time: Evaluating Temporal Dynamics in Spoken Language Models","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09643","citing_title":"MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2603.17837","citing_title":"The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12034","citing_title":"Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2507.08128","citing_title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13841","citing_title":"EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12034","citing_title":"Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27393","citing_title":"MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2504.18425","citing_title":"Kimi-Audio Technical Report","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11594","citing_title":"HumDial-EIBench: A Human-Recorded Multi-Turn Emotional Intelligence Benchmark for Audio Language Models","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06897","citing_title":"MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2503.20215","citing_title":"Qwen2.5-Omni Technical Report","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15037","citing_title":"From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14604","citing_title":"Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14548","citing_title":"VoxSafeBench: Not Just What Is Said, but Who, How, and Where","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16659","citing_title":"Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22821","citing_title":"Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00022","citing_title":"Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20842","citing_title":"SpeechParaling-Bench: A Comprehensive Benchmark for Paralinguistic-Aware Speech Generation","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF","json":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF.json","graph_json":"https://pith.science/api/pith-number/XDRDHMN3T3SQAVSFP2ZCKABITF/graph.json","events_json":"https://pith.science/api/pith-number/XDRDHMN3T3SQAVSFP2ZCKABITF/events.json","paper":"https://pith.science/paper/XDRDHMN3"},"agent_actions":{"view_html":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF","download_json":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF.json","view_paper":"https://pith.science/paper/XDRDHMN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17196&json=true","fetch_graph":"https://pith.science/api/pith-number/XDRDHMN3T3SQAVSFP2ZCKABITF/graph.json","fetch_events":"https://pith.science/api/pith-number/XDRDHMN3T3SQAVSFP2ZCKABITF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/action/storage_attestation","attest_author":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/action/author_attestation","sign_citation":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/action/citation_signature","submit_replication":"https://pith.science/pith/XDRDHMN3T3SQAVSFP2ZCKABITF/action/replication_record"}},"created_at":"2026-05-17T23:38:46.069112+00:00","updated_at":"2026-05-17T23:38:46.069112+00:00"}