# Speech Recognition Model Improves Text-to-Speech Synthesis using Fine-Grained Reward

arXiv: https://arxiv.org/abs/2511.17555 · HTML: https://mlsanity.com/paper/2511.17555/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 12 Nov 2025.

## Builds on (most cited first, 23 of 23)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [Fine-Grained Human Feedback Gives Better Rewards for Language Model Training](https://mlsanity.com/paper/2306.01693/) (2023)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Secrets of RLHF in Large Language Models Part I: PPO](https://mlsanity.com/paper/2307.04964/) (2023)
- [Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation](https://mlsanity.com/paper/2407.05361/) (2024)
- [MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformer](https://mlsanity.com/paper/2409.00750/) (2024)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)
- [VoiceCraft: Zero-Shot Speech Editing and Text-to-Speech in the Wild](https://mlsanity.com/paper/2403.16973/) (2024)
- [Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens](https://mlsanity.com/paper/2503.01710/) (2025)
- [AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec](https://mlsanity.com/paper/2305.16608/) (2023)
- [SpeechAlign: Aligning Speech Generation to Human Preferences](https://mlsanity.com/paper/2404.05600/) (2024)
- [Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers](https://mlsanity.com/paper/2409.03621/) (2024)
- [VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech](https://mlsanity.com/paper/2401.14321/) (2024)
- [Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment](https://mlsanity.com/paper/2406.17957/) (2024)
- [Preference Alignment Improves Language Model-Based TTS](https://mlsanity.com/paper/2409.12403/) (2024)
- [Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback](https://mlsanity.com/paper/2406.00654/) (2024)
- [Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization](https://mlsanity.com/paper/2407.02243/) (2024)
- [Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models](https://mlsanity.com/paper/2405.14161/) (2024)

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

- [HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech](https://mlsanity.com/paper/2606.28249/) (2026)

## Abstract (arXiv)

Recent advances in text-to-speech (TTS) have enabled models to clone arbitrary unseen speakers and synthesize high-quality, natural-sounding speech. However, evaluation methods lag behind: typical mean opinion score (MOS) estimators perform regression over entire utterances, while failures usually occur in a few problematic words. We observe that encoder-decoder ASR models (e.g., Whisper) surface word-level mismatches between speech and text via cross-attention, providing a fine-grained reward signal. Building on this, we introduce Word-level TTS Alignment by ASR-driven Attentive Reward (W3AR). Without explicit reward annotations, W3AR uses attention from a pre-trained ASR model to drive finer-grained alignment and optimization of sequences predicted by a TTS model. Experiments show that W3AR improves the quality of existing TTS systems and strengthens zero-shot robustness on unseen speakers. More broadly, our results suggest a simple recipe for generative modeling: understanding models can act as evaluators, delivering informative, fine-grained feedback for optimization.