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 com

Stats

• citations23
• S2 citations—
• github stars0
• HF likes0
• heat score10.35
• arxiv keybollepalli2019generative

Related papers

• Waveform Generation For Text-to-speech Synthesis Using Pitch-synchronous Multi-scale Generative Adversarial Networks (2018)8.35
• Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks (2017)16.21
• Analysis By Adversarial Synthesis -- A Novel Approach For Speech Vocoding (2019)3.58
• High Fidelity Speech Synthesis With Adversarial Networks (2019)0.00
• Wasserstein GAN And Waveform Loss-based Acoustic Model Training For Multi-speaker Text-to-speech Synthesis Systems Using A Wavenet Vocoder (2018)12.61
• Speaker-independent Raw Waveform Model For Glottal Excitation (2018)9.76
• End-to-end Video-to-speech Synthesis Using Generative Adversarial Networks (2021)11.58
• A Comparison Of Recent Waveform Generation And Acoustic Modeling Methods For Neural-network-based Speech Synthesis (2018)11.76