# Explore the Reinforcement Learning for the LLM based ASR and TTS system

arXiv: https://arxiv.org/abs/2509.18569 · HTML: https://mlsanity.com/paper/2509.18569/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 16 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Seed-TTS: A Family of High-Quality Versatile Speech Generation Models](https://mlsanity.com/paper/2406.02430/) (2024)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [Step-Audio 2 Technical Report](https://mlsanity.com/paper/2507.16632/) (2025)
- [Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Models](https://mlsanity.com/paper/1712.01818/) (2017)
- [Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering](https://mlsanity.com/paper/2503.11197/) (2025)
- [Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition](https://mlsanity.com/paper/2407.04675/) (2024)
- [Fun-ASR Technical Report](https://mlsanity.com/paper/2509.12508/) (2025)
- [Differentiable Reward Optimization for LLM based TTS system](https://mlsanity.com/paper/2507.05911/) (2025)

## Built on by (most cited first, 3 of 3)

- [GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech model](https://mlsanity.com/paper/2608.03215/) (2026)
- [Investigating Group Relative Policy Optimization for Diffusion Transformer based Text-to-Audio Generation](https://mlsanity.com/paper/2603.01565/) (2026)
- [Bridging What the Model Thinks and How It Speaks: Expressive Speech Generation via Self-Aware Intent-Realization Alignment](https://mlsanity.com/paper/2604.11424/) (2026)

## Abstract (arXiv)

In recent years, large language models (LLMs) have played an important role in automatic speech recognition (ASR) and text-to-speech (TTS) systems. While reinforcement learning (RL) has significantly enhanced LLM performance in text-based tasks, its application to ASR and TTS remains underexplored due to the complexity of training audio-based models. In this study, we propose a lightweight RL framework tailored for audio-based LLMs that can process audio inputs and generate audio outputs. Based on this framework, we evaluate the effectiveness of reinforcement learning on both ASR and TTS tasks. For the ASR task, we experiment with different rule-based reward functions within the Group Relative Policy Optimization (GRPO) framework and investigate the impact of RL data construction. For the TTS task, we compare GRPO with Differentiable Reward Optimization (DiffRO) and further combine the two approaches to achieve improved performance. Our experiments demonstrate that RL can significantly enhance the performance of both ASR and TTS systems, even with limited training data and a small number of optimization steps.