Generative adversarial network-based glottal waveform model for statistical parametric speech synthesis

Abstract

Recent studies have shown that text-to-speech synthesis quality can be improved by using glottal vocoding. This refers to vocoders that parameterize speech into two parts, the glottal excitation and vocal tract, that occur in the human speech production apparatus. Current glottal vocoders generate the glottal excitation waveform by using deep neural networks (DNNs). However, the squared error-based training of the present glottal excitation models is limited to generating conditional average waveforms, which fails to capture the stochastic variation of the waveforms. As a result, shaped noise is added as post-processing. In this study, we propose a new method for predicting glottal waveforms by generative adversarial networks (GANs). GANs are generative models that aim to embed the data distribution in a latent space, enabling generation of new instances very similar to the original by randomly sampling the latent distribution. The glottal pulses generated by GANs show a stochastic component similar to natural glottal pulses. In our experiments, we compare synthetic speech generated using glottal waveforms produced by both DNNs and GANs. The results show that the newly proposed GANs achieve synthesis quality comparable to that of widely-used DNNs, without using an additive noise component.

Accepted in Interspeech

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• WaveNet: A Generative Model for Raw Audio
• Deep Voice: Real-time Neural Text-to-Speech
• Least Squares Generative Adversarial Networks
• Raw Waveform-based Speech Enhancement by Fully Convolutional Networks

Cited by in corpus (12)

• Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends
• Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
• The Ethical Implications of Generative Audio Models: A Systematic Literature Review
• Probability density distillation with generative adversarial networks for high-quality parallel waveform generation
• Adversarially Trained Multi-Singer Sequence-To-Sequence Singing Synthesizer
• Wavebender GAN: An architecture for phonetically meaningful speech manipulation
• Improved parallel WaveGAN vocoder with perceptually weighted spectrogram loss
• Unified Source-Filter GAN: Unified Source-filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN
• A Novel Framework for Selection of GANs for an Application
• Conditioning Trick for Training Stable GANs
• A Survey on GAN Acceleration Using Memory Compression Technique
• Improving Stability of LS-GANs for Audio and Speech Signals