Reducing Over-smoothness In Speech Synthesis Using Generative Adversarial Networks

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.

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keysheng2018reducing

Related papers

• Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks (2017)16.21
• Exploring Speech Enhancement With Generative Adversarial Networks For Robust Speech Recognition (2017)16.14
• Video-driven Speech Reconstruction Using Generative Adversarial Networks (2019)11.39
• Towards Generalized Speech Enhancement With Generative Adversarial Networks (2019)10.35
• End-to-end Video-to-speech Synthesis Using Generative Adversarial Networks (2021)11.58
• On Enhancing Speech Emotion Recognition Using Generative Adversarial Networks (2018)12.33
• Hifi-gan: Generative Adversarial Networks For Efficient And High Fidelity Speech Synthesis (2020)0.00
• Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework (2017)10.21