Reducing over-smoothness in speech synthesis using Generative Adversarial Networks
2019 International Multi-Conference on Engineering, Computer and Information Sciences (SIBIRCON)2019pp. 0972–0974
Citations Over TimeTop 23% of 2019 papers
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.
Related Papers
- → Natural Speech Synthesizer for Blind Persons Using Hybrid Approach(2014)14 cited
- → A new Chinese text-to-speech system with high naturalness(2002)15 cited
- → Text to speech synthesis(2024)1 cited
- Removing Preglottalization from Unit-Selection Synthesis: Towards the Linguistic Naturalness of Synthetic Czech Speech(2012)
- → Prosody Correction Preserving Speaker Individuality for Chinese-Accented Japanese HMM-Based Text-to-Speech Synthesis(2019)