2 papers
cs.SD2026
Listen, Think, Transcribe: Continuous Latent Test-Time Scaling for ASR
Ho Lam Chung, Yiming Chen, Dau-Cheng Lyu +2
End-to-end ASR models transcribe in a single pass, leaving no room for the decoder to revisit hard inputs. We propose LatentASR, a parameter-efficient method that adds continuous l…
cs.CL2026
ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models
Chi-Yuan Hsiao, Ke-Han Lu, Yu-Kuan Fu +3
End-to-end full-duplex Speech Language Models (SLMs) require precise turn-taking for natural interaction. However, optimizing temporal dynamics via standard raw-token reinforcement…