Author

Pierre-Edouard Honnet

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Sep 2026

Controlling Speaking Rate in Autoregressive TTS via Activation Steering

Autoregressive text-to-speech (TTS) systems synthesize natural speech but, once trained, offer little control over speaking rate. We show that speaking rate can be steered at inference time, without retraining, by clamping a single decoder block's activation along a discovered speed axis. A decoder-block analysis recov...

Francesco Verdini, Antonis Asonitis, Aref Farhadipour et al. · arXiv.org · 0 citations

#machine learning Preprint Jul 2026

The Limits of Reference-Free Speech Quality Metrics as Evaluators and Rewards on Modern Text-to-Speech

This work evaluates six human-rated corpora spanning the quality range from artifact-rich to defect-free TTS, evaluating each predictor on a pairwise task that asks whether the clip it scores higher is the clip listeners prefer, and subjects interpretable prosodic and signal-processing features to the same protocol.

Antonis Asonitis, Juan Pablo Zuluaga Gomez, Francesco Verdini et al. · 2 citations