Reducing over-smoothness in speech synthesis using Generative Adversarial Networks
arXiv:1810.10989
Abstract
Speech synthesis is widely used in many practical applications. In recent years, speech synthesis technology has developed rapidly. However, one of the reasons why synthetic speech is unnatural is that it often has over-smoothness. In order to improve the naturalness of synthetic speech, we first extract the mel-spectrogram of speech and convert it into a real image, then take the over-smooth mel-spectrogram image as input, and use image-to-image translation Generative Adversarial Networks(GANs) framework to generate a more realistic mel-spectrogram. Finally, the results show that this method greatly reduces the over-smoothness of synthesized speech and is more close to the mel-spectrogram of real speech.
arXiv commentAccepted by Siberian Symposium on Data Science and Engineering (SSDSE) 2018
References in corpus (7)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- WaveNet: A Generative Model for Raw Audio
- Striving for Simplicity: The All Convolutional Net
- Deep Voice: Real-time Neural Text-to-Speech
- Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
- Deep Voice 2: Multi-Speaker Neural Text-to-Speech
- Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder