AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning

arXiv:2510.05478 · eess.AS · Submitted 2025-10-07 · Read on arXiv

eess.AS

Submitted: 2025-10-07

Updated: 2026-10-29

Terminology

• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Pseudo-labels — 1× in this paper · explained in 2 episodes

Related papers

• Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy
• SLT 2026 REAL-TSE Challenge: Real-world Target Speaker Extraction from Conversational Recordings
• Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
• X-VC: Zero-shot Streaming Voice Conversion in Codec Space
• Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
• LiveAnon: Improving Privacy and Utility in Streaming Speaker Anonymization with Codec Language Models