Trendoday

WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning

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 trajec

  • Upvotes8
–Rank now
#12Peak rank
3Days on list
299Score · 7d
Nov 11, 2026First seen
Rank · 7 days

About this paper

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.

Trending history

WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning was first seen on Hugging Face · Daily papers on Nov 11, 2026. Since then it has appeared in 22 checks on 3 different days. Its best position was #12 of 30, reached on Nov 11, 19:28 UTC. It dropped off the list after Nov 13, 05:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 11:2821:5808:2818:5805:28 Nov 11, 11:28 UTC · #17Nov 11, 13:28 UTC · #14Nov 11, 15:28 UTC · #13Nov 11, 17:28 UTC · #13Nov 11, 19:28 UTC · #12Nov 11, 21:28 UTC · #14Nov 11, 23:28 UTC · #14Nov 12, 01:28 UTC · #14Nov 12, 03:28 UTC · #13Nov 12, 05:28 UTC · #14Nov 12, 07:28 UTC · #14Nov 12, 09:28 UTC · #14Nov 12, 11:28 UTC · #13Nov 12, 13:28 UTC · #13Nov 12, 15:28 UTC · #13Nov 12, 17:28 UTC · #13Nov 12, 19:28 UTC · #13Nov 12, 21:28 UTC · #14Nov 12, 23:28 UTC · #14Nov 13, 01:28 UTC · #13Nov 13, 03:28 UTC · #13Nov 13, 05:28 UTC · #12

Last 14 days

Best rank per day (UTC).

Nov 3today

Metric history

Platform metric as reported by Hugging Face.

061117 11:2821:5808:2818:5805:28 Nov 11, 11:28 UTC · 8Nov 11, 13:28 UTC · 11Nov 11, 15:28 UTC · 13Nov 11, 17:28 UTC · 13Nov 11, 19:28 UTC · 13Nov 11, 21:28 UTC · 13Nov 11, 23:28 UTC · 13Nov 12, 01:28 UTC · 13Nov 12, 03:28 UTC · 15Nov 12, 05:28 UTC · 15Nov 12, 07:28 UTC · 17Nov 12, 09:28 UTC · 17Nov 12, 11:28 UTC · 17Nov 12, 13:28 UTC · 17Nov 12, 15:28 UTC · 17Nov 12, 17:28 UTC · 17Nov 12, 19:28 UTC · 17Nov 12, 21:28 UTC · 17Nov 12, 23:28 UTC · 17Nov 13, 01:28 UTC · 17Nov 13, 03:28 UTC · 17Nov 13, 05:28 UTC · 17

Questions

Is WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 13, 05:28 UTC, after 3 days of trending.

What is the highest rank WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning reached?

#12 on Hugging Face · Daily papers, on Nov 11, 19:28 UTC. Trendoday checks this list every 120 minutes.

How long has WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning been trending?

It was first seen on Nov 11, 2026 and has been on the list on 3 days (22 checks) since.