HooliGAN: Robust, High Quality Neural Vocoding

Abstract

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/

References in corpus (6)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• On the Variance of the Adaptive Learning Rate and Beyond
• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions
• Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
• Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis

Cited by in corpus (5)

• WaveGrad: Estimating Gradients for Waveform Generation
• The Ethical Implications of Generative Audio Models: A Systematic Literature Review
• WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
• Unified Source-Filter GAN: Unified Source-filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN
• AdaVocoder: Adaptive Vocoder for Custom Voice