WaveGen is a fully end-to-end diffusion framework for text-to-waveform generation that jointly learns spectral and waveform trajectories via Spectral Forcing without external audio codecs, vocoders, latent models, alignment modules, or self-supervised representations, achieving state-of-the-art…
This work proposes WaveGen, a fully end-to-end diffusion-based text-to-waveform framework based on Spectral Forcing, which jointly learns an internal spectral trajectory and the target waveform trajectory within a single model, enabling direct end-to-end text-to-waveform generation. Unlike recent TTS pipelines, WaveGen does not rely on separately trained or externally decoded intermediate representations, such as neural audio codecs, Mel-spectrogram vocoders, or VAE-based latent models. In addition, WaveGen performs internal text-speech alignment within a single model, eliminating the need for external alignment modules such as duration predictors. To preserve a truly end-to-end…
diffusion-based text-to-waveformSpectral Forcingend-to-end text-to-waveform generationTTS pipelinesneural audio codecsMel-spectrogram vocodersVAE-based latent modelsinternal text-speech alignmentduration predictorsself-supervised representations
- Upvotes
- 8
- Authors
- 2
- Published
- Nov 9, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.