# Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimization

arXiv: https://arxiv.org/abs/2509.21718 · HTML: https://mlsanity.com/paper/2509.21718/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Preference alignment for recommenders and RAG, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 19 of its 22 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Preference alignment for recommenders and RAG](https://mlsanity.com/alignment/preference-alignment-for-recommenders-and-rag/)

## Builds on (most cited first, 19 of 19)

- [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)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [SpeechX: Neural Codec Language Model as a Versatile Speech Transformer](https://mlsanity.com/paper/2308.06873/) (2023)
- [TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context](https://mlsanity.com/paper/2110.04410/) (2021)
- [Hi-Fi Multi-Speaker English TTS Dataset](https://mlsanity.com/paper/2104.01497/) (2021)
- [TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio](https://mlsanity.com/paper/2304.01448/) (2023)
- [ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering](https://mlsanity.com/paper/2401.07333/) (2024)
- [SpeechAlign: Aligning Speech Generation to Human Preferences](https://mlsanity.com/paper/2404.05600/) (2024)
- [End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learning](https://mlsanity.com/paper/1904.06508/) (2019)
- [Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance](https://mlsanity.com/paper/2502.05236/) (2025)
- [Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment](https://mlsanity.com/paper/2406.17957/) (2024)
- [Low-Resource Multilingual and Zero-Shot Multispeaker TTS](https://mlsanity.com/paper/2210.12223/) (2022)
- [CML-TTS A Multilingual Dataset for Speech Synthesis in Low-Resource Languages](https://mlsanity.com/paper/2306.10097/) (2023)
- [NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference](https://mlsanity.com/paper/2508.05835/) (2025)

## Built on by (most cited first, 1 of 1)

- [Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs](https://mlsanity.com/paper/2606.18323/) (2026)

## Abstract (arXiv)

Developing high-quality text-to-speech (TTS) systems for low-resource languages is challenging due to the scarcity of paired text and speech data. In contrast, automatic speech recognition (ASR) models for such languages are often more accessible, owing to large-scale multilingual pre-training efforts. We propose a framework based on Group Relative Policy Optimization (GRPO) to adapt an autoregressive, multilingual TTS model to new languages. Our method first establishes a language-agnostic foundation for TTS synthesis by training a multilingual baseline with International Phonetic Alphabet (IPA) tokens. Next, we fine-tune this model on limited paired data of the new languages to capture the target language's prosodic features. Finally, we apply GRPO to optimize the model using only unpaired text and speaker prompts, guided by a multi-objective reward from pretrained ASR, speaker verification, and audio quality estimation models. Experiments demonstrate that this pipeline produces intelligible and speaker-consistent speech in low-resource languages, substantially outperforming fine-tuning alone. Furthermore, our GRPO-based framework also improves TTS performance in high-resource languages, surpassing offline alignment methods such as Direct Preference Optimization (DPO) yielding superior intelligibility, speaker similarity, and audio quality.