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

03/14/2019
by   Bajibabu Bollepalli, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/23/2017

Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks

A method for statistical parametric speech synthesis incorporating gener...
research
04/03/2018

Speech waveform synthesis from MFCC sequences with generative adversarial networks

This paper proposes a method for generating speech from filterbank mel f...
research
10/25/2018

Reducing over-smoothness in speech synthesis using Generative Adversarial Networks

Speech synthesis is widely used in many practical applications. In recen...
research
07/01/2019

Analysis by Adversarial Synthesis -- A Novel Approach for Speech Vocoding

Classical parametric speech coding techniques provide a compact represen...
research
10/06/2021

GANtron: Emotional Speech Synthesis with Generative Adversarial Networks

Speech synthesis is used in a wide variety of industries. Nonetheless, i...
research
04/12/2017

Sampling-based speech parameter generation using moment-matching networks

This paper presents sampling-based speech parameter generation using mom...
research
04/16/2019

Expediting TTS Synthesis with Adversarial Vocoding

Recent approaches in text-to-speech (TTS) synthesis employ neural networ...

Please sign up or login with your details

Forgot password? Click here to reset