HiFi-Glot: High-Fidelity Neural Formant Synthesis with Differentiable Resonant Filters

TL;DR

HiFi-Glot is an end-to-end neural formant synthesis system that combines precise formant control with high-fidelity speech generation, improving naturalness and controllability over existing methods.

Contribution

It introduces a neural source-filter model with differentiable resonant filters for high-quality, controllable speech synthesis, surpassing traditional formant manipulation tools.

Findings

Higher perceptual quality and naturalness in synthesized speech

More precise control over formant frequencies

Outperforms Praat in formant manipulation tasks

Abstract

Formant synthesis aims to generate speech with controllable formant structures, enabling precise control of vocal resonance and phonetic features. However, while existing formant synthesis approaches enable precise formant manipulation, they often yield an impoverished speech signal by failing to capture the complex co-occurring acoustic cues essential for naturalness. To address this issue, this letter presents HiFi-Glot, an end-to-end neural formant synthesis system that achieves both precise formant control and high-fidelity speech synthesis. Specifically, the proposed model adopts a source--filter architecture inspired by classical formant synthesis, where a neural vocoder generates the glottal excitation signal, and differentiable resonant filters model the formants to produce the speech waveform. Experiment results demonstrate that our proposed HiFi-Glot model can generate speech with higher perceptual quality and naturalness while exhibiting a more precise control over formant frequencies, outperforming industry-standard formant manipulation tools such as Praat. Code, checkpoints, and representative audio samples are available at https://www.yichenggu.com/HiFi-Glot/.