Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform
This work addresses the need for faster and more efficient text-to-speech synthesis for applications requiring real-time performance, though it is incremental as it builds upon the existing VITS model.
The paper tackles the problem of inefficient inference in high-quality text-to-speech models by proposing a lightweight end-to-end model using multi-band generation and inverse short-time Fourier transform, achieving a real-time factor of 0.066 on an Intel Core i7 CPU, which is 4.1 times faster than VITS while maintaining similar naturalness.
We propose a lightweight end-to-end text-to-speech model using multi-band generation and inverse short-time Fourier transform. Our model is based on VITS, a high-quality end-to-end text-to-speech model, but adopts two changes for more efficient inference: 1) the most computationally expensive component is partially replaced with a simple inverse short-time Fourier transform, and 2) multi-band generation, with fixed or trainable synthesis filters, is used to generate waveforms. Unlike conventional lightweight models, which employ optimization or knowledge distillation separately to train two cascaded components, our method enjoys the full benefits of end-to-end optimization. Experimental results show that our model synthesized speech as natural as that synthesized by VITS, while achieving a real-time factor of 0.066 on an Intel Core i7 CPU, 4.1 times faster than VITS. Moreover, a smaller version of the model significantly outperformed a lightweight baseline model with respect to both naturalness and inference speed. Code and audio samples are available from https://github.com/MasayaKawamura/MB-iSTFT-VITS.