Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder

by   Yi Zhao, et al.

Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to vocoders and hence they are often called neural vocoders. The neural vocoder uses acoustic features as local condition parameters, and these parameters need to be accurately predicted by another acoustic model. However, it is not yet clear how to train this acoustic model, which is problematic because the final quality of synthetic speech is significantly affected by the performance of the acoustic model. Significant degradation happens, especially when predicted acoustic features have mismatched characteristics compared to natural ones. In order to reduce the mismatched characteristics between natural and generated acoustic features, we propose frameworks that incorporate either a conditional generative adversarial network (GAN) or its variant, Wasserstein GAN with gradient penalty (WGAN-GP), into multi-speaker speech synthesis that uses the WaveNet vocoder. We also extend the GAN frameworks and use the discretized mixture logistic loss of a well-trained WaveNet in addition to mean squared error and adversarial losses as parts of objective functions. Experimental results show that acoustic models trained using the WGAN-GP framework using back-propagated discretized-mixture-of-logistics (DML) loss achieves the highest subjective evaluation scores in terms of both quality and speaker similarity.


page 1

page 3

page 4

page 5

page 7

page 9


GELP: GAN-Excited Liner Prediction for Speech Synthesis from Mel-spectrogram

Recent advances in neural network -based text-to-speech have reached hum...

Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems

Automatic speaker verification (ASV) systems use a playback detector to ...

GELP: GAN-Excited Linear Prediction for Speech Synthesis from Mel-spectrogram

Recent advances in neural network -based text-to-speech have reached hum...

Karaoker: Alignment-free singing voice synthesis with speech training data

Existing singing voice synthesis models (SVS) are usually trained on sin...

Generative Adversarial Network based Speaker Adaptation for High Fidelity WaveNet Vocoder

Neural networks based vocoders, typically the WaveNet, have achieved spe...

Sampling Using Neural Networks for colorizing the grayscale images

The main idea of this paper is to explore the possibilities of generatin...

Towards Robust Waveform-Based Acoustic Models

We propose an approach for learning robust acoustic models in adverse en...

Please sign up or login with your details

Forgot password? Click here to reset