Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASR

arXiv:2608.03610 · cs.CL, cs.SD, eess.AS · Submitted 2026-08-10 · Read on arXiv

Yuan Xie, Jiaqi Song, Xianliang Wang, Ming Lei, Jie Gao, Jie Wu

cs.CL, cs.SD, eess.AS

Submitted: 2026-08-10

Updated: 2026-08-11

Code: https://github.com/wenet-e2e/WeTextProcessing

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 31× in this paper · explained in 2 episodes
• Benchmark — 15× in this paper · explained in 2 episodes
• On-Policy Distillation — 13× in this paper · explained in 3 episodes
• Policy distillation — 13× in this paper · explained in 2 episodes
• Decoder — 7× in this paper · explained in 2 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Embeddings — 5× in this paper · explained in 2 episodes
• Consistency — 4× in this paper · explained in 3 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• RLVR — 2× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 26 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Decoupled Clip and Dynamic Sampling Policy Optimization — 1× in this paper
• Decoupling — 1× in this paper · explained in 2 episodes
• Meta-learning — 1× in this paper · explained in 3 episodes
• On-Policy Distillation (OPD) — 1× in this paper · explained in 7 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning with Verifiable Rewards (RLVR) — 1× in this paper · explained in 3 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes

Sources

• Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
• Fun-ASR Technical Report
• Qwen3-ASR Technical Report
• Investigating the Impact of Cross-lingual Acoustic-Phonetic Similarities on Multilingual Speech Recognition
• MiMo-V2-Flash Technical Report
• MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
• Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System
• NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
• Language-Aware Distillation for Multilingual Instruction-Following Speech LLMs with ASR-Only Supervision
• Step-Audio 2 Technical Report
• Qwen3-Omni Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering