# FlexSpeech: Towards Stable, Controllable and Expressive Text-to-Speech

arXiv: https://arxiv.org/abs/2505.05159 · HTML: https://mlsanity.com/paper/2505.05159/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Vocoders and speech synthesis, one of 11 directions in Speech and audio language models.
- Builds on 28 of its 50 references that are in the map.
- First posted on arXiv 8 May 2025.

## Placed in

- Speech and audio language models / [Vocoders and speech synthesis](https://mlsanity.com/speech/vocoders-and-speech-synthesis/)

## Builds on (most cited first, 28 of 28)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech](https://mlsanity.com/paper/2105.06337/) (2021)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models](https://mlsanity.com/paper/2403.03100/) (2024)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision](https://mlsanity.com/paper/2302.03540/) (2023)
- [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)
- [Autoregressive Speech Synthesis without Vector Quantization](https://mlsanity.com/paper/2407.08551/) (2024)
- [Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis](https://mlsanity.com/paper/2411.01156/) (2024)
- [SpeechAlign: Aligning Speech Generation to Human Preferences](https://mlsanity.com/paper/2404.05600/) (2024)
- [Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis](https://mlsanity.com/paper/2307.07218/) (2023)
- [DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021](https://mlsanity.com/paper/2110.12612/) (2021)
- [Preference Alignment Improves Language Model-Based TTS](https://mlsanity.com/paper/2409.12403/) (2024)
- [Continuous Speech Tokenizer in Text To Speech](https://mlsanity.com/paper/2410.17081/) (2024)
- [StoryTTS: A Highly Expressive Text-to-Speech Dataset with Rich Textual Expressiveness Annotations](https://mlsanity.com/paper/2404.14946/) (2024)

## Abstract (arXiv)

Current speech generation research can be categorized into two primary classes: non-autoregressive and autoregressive. The fundamental distinction between these approaches lies in the duration prediction strategy employed for predictable-length sequences. The NAR methods ensure stability in speech generation by explicitly and independently modeling the duration of each phonetic unit. Conversely, AR methods employ an autoregressive paradigm to predict the compressed speech token by implicitly modeling duration with Markov properties. Although this approach improves prosody, it does not provide the structural guarantees necessary for stability. To simultaneously address the issues of stability and naturalness in speech generation, we propose FlexSpeech, a stable, controllable, and expressive TTS model. The motivation behind FlexSpeech is to incorporate Markov dependencies and preference optimization directly on the duration predictor to boost its naturalness while maintaining explicit modeling of the phonetic units to ensure stability. Specifically, we decompose the speech generation task into two components: an AR duration predictor and a NAR acoustic model. The acoustic model is trained on a substantial amount of data to learn to render audio more stably, given reference audio prosody and phone durations. The duration predictor is optimized in a lightweight manner for different stylistic variations, thereby enabling rapid style transfer while maintaining a decoupled relationship with the specified speaker timbre. Experimental results demonstrate that our approach achieves SOTA stability and naturalness in zero-shot TTS. More importantly, when transferring to a specific stylistic domain, we can accomplish lightweight optimization of the duration module solely with about 100 data samples, without the need to adjust the acoustic model, thereby enabling rapid and stable style transfer.