HooliGAN: Robust, High Quality Neural Vocoding
This addresses the need for efficient and high-quality speech synthesis tools for applications in AI and audio processing, though it appears incremental by combining existing ideas.
The paper tackled the problem of generating high-quality speech audio by introducing HooliGAN, a robust vocoder that achieves state-of-the-art results, fine-tunes well with small datasets under 30 minutes, and generates audio at 2.2MHz on GPU and 35kHz on CPU.
Recent developments in generative models have shown that deep learning combined with traditional digital signal processing (DSP) techniques could successfully generate convincing violin samples [1], that source-excitation combined with WaveNet yields high-quality vocoders [2, 3] and that generative adversarial network (GAN) training can improve naturalness [4, 5]. By combining the ideas in these models we introduce HooliGAN, a robust vocoder that has state of the art results, finetunes very well to smaller datasets (<30 minutes of speechdata) and generates audio at 2.2MHz on GPU and 35kHz on CPU. We also show a simple modification to Tacotron-basedmodels that allows seamless integration with HooliGAN. Results from our listening tests show the proposed model's ability to consistently output high-quality audio with a variety of datasets, big and small. We provide samples at the following demo page: https://resemble-ai.github.io/hooligan_demo/