Look Less, Hear Better: Jointly Rewarded GRPO for Streaming ASR
cs.SD, cs.AI
Submitted: 2026-09-16
Updated: 2026-09-16
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Voxtral Realtime
- Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Group Relative Policy Optimization for Speech Recognition
- GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
- Qwen3-ASR Technical Report
- Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
- Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment