NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
26 results for “keyword:"speech language models"” in ICLR 2027. 5 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]MEmoS2S-Bench: An Open-Ended Benchmark for Emotional Understanding, Reasoning, and Empathetic Spoken Response Generation in Multilingual Speech-LLMs▼1.2k1.67
[PDF]Crescendo-Live: Multi-Turn Jailbreaks of Full-Duplex Speech Models in Live Calls and Their Defense with Daimonion▲3.0k2.50
[PDF]FINE-GRAINED DEVICE-DIRECTED SPEECH RECOGNITION: FROM OFFLINE MODELING TO STREAMING INFERENCE▼1351.33
[PDF]APEX-Voice: Can Voice Agents Complete Professional Workflows Through Full-Duplex Interaction▼1.2k1.67
[PDF]DuplexSpeechBench–IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice Agents▼4.3k2.00
[PDF]One Token per Speaker: An Omni-Native, Exchangeable Entity Interface for Conversational Memory Routing▲20k2.67
[PDF]Collapse, Repair, and Drift: Dissecting Fine Tuning Dynamics in Speech Language Models▼1.2k1.67
[PDF]Bridge-Duplex: Bridging Semantic and Generative Streams for Full-Duplex Speech-to-Speech Dialogue▲4002.67
[PDF]CueDuet: Distilling What to Say and How to Speak for Paralinguistic-Aware Spoken Dialogue▼4.5k2.67
[PDF]The Perception-Override Reflex: When Speech Language Models Follow Perception Over Instructions▲6.1k2.00
[PDF]ControlAnything: Unified word-level, Intensity-Aware, and Composable Control for Expressive Text-to-Speech▲4002.67
[PDF]Text Scores Do Not Establish Performance on Lexically Non-Diagnostic Speech Tasks: A Qwen2-Audio Quantization Case Study▲3.9k1.75
Withdrawn or desk rejected (5)
[PDF]DynaEmpathy: Benchmarking and Training Speech Language Models for Interactive Empathetic Spoken DialogueWithdrawn2.00