# BareWave: Waveform-Native Flow-Matching Text-to-Speech

arXiv: https://arxiv.org/abs/2606.09048 · HTML: https://mlsanity.com/paper/2606.09048/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 24 of 24)

- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale](https://mlsanity.com/paper/2306.15687/) (2023)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation](https://mlsanity.com/paper/2407.05361/) (2024)
- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [E2 TTS: Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS](https://mlsanity.com/paper/2406.18009/) (2024)
- [PixelDiT: Pixel Diffusion Transformers for Image Generation](https://mlsanity.com/paper/2511.20645/) (2025)
- [DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation](https://mlsanity.com/paper/2511.19365/) (2025)
- [DiP: Taming Diffusion Models in Pixel Space](https://mlsanity.com/paper/2511.18822/) (2025)
- [JetFormer: An Autoregressive Generative Model of Raw Images and Text](https://mlsanity.com/paper/2411.19722/) (2024)
- [Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis](https://mlsanity.com/paper/2011.03568/) (2020)
- [E3 TTS: Easy End-to-End Diffusion-based Text to Speech](https://mlsanity.com/paper/2311.00945/) (2023)
- [DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation](https://mlsanity.com/paper/2310.01381/) (2023)
- [WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching](https://mlsanity.com/paper/2503.16689/) (2025)
- [Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment](https://mlsanity.com/paper/2505.19595/) (2025)

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

- [Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens](https://mlsanity.com/paper/2607.29363/) (2026)

## Abstract (arXiv)

Removing intermediate representations and separately trained decoding stages has become an important direction in generative modeling. In text-to-speech, however, high-quality systems are still commonly built through an intermediate acoustic representation before waveform synthesis. In this work, we present BareWave, a fully waveform-native framework for direct text-to-wave generation in flow-matching TTS. We consider this setting to raise three training challenges: raw-waveform modeling lacks a strong pretrained representational scaffold, different stages of training benefit from different noise schedules, and data-space perceptual objectives do not automatically share the temporal structure of the velocity-space flow objective. As a result, direct waveform training is hard to optimize efficiently, hard to push toward a strong final operating point with a fixed recipe, and hard to integrate effective perceptual refinement. Guided by this view, we develop a direct text-to-wave training framework that combines training-time representation alignment, staged noise scheduling, and velocity-aware perceptual alignment (VAPA), while preserving a single waveform-native inference path without pretrained components at test time. Experiments on zero-shot voice cloning show that strong intelligibility, speaker similarity, and naturalness can be achieved under a fully waveform-native inference path, supporting waveform-native flow-matching TTS as a practical direction. Project page with audio demos is available at https://barewave.github.io/.