VoxMel TTS Technical Report
Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed
- Upvotes19
Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed
VoxMel is a tokenizer-free autoregressive TTS framework that uses an invertible two-axis Haar transform to decompose mel spectrograms into Coarse-Mel and residual tiers, enabling stable high-fidelity generation with strong recognition and speaker-similarity results.
Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed representations (e.g., continuous VAE latents) to render prediction tractable, they rely on complex neural encoders that often cap generation fidelity. Conversely, training-free targets like mel-spectrograms eliminate encoder overhead, yet their potential for autoregressive generation remains largely underexplored. In this work, we propose VoxMel, a tokenizer-free framework for autoregressive TTS that makes stable mel modeling tractable through a fixed, exactly invertible two-axis Haar…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
VoxMel TTS Technical Report was first seen on Hugging Face · Daily papers on Nov 17, 2026. Since then it has appeared in 10 checks on 2 different days. Its best position was #9 of 30, reached on Nov 17, 21:28 UTC. It dropped off the list after Nov 18, 03:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 18, 03:28 UTC, after 2 days of trending.
#9 on Hugging Face · Daily papers, on Nov 17, 21:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 17, 2026 and has been on the list on 2 days (10 checks) since.