High-quality Speech Synthesis Using Super-resolution Mel-Spectrogram

Evgeniy Pavlovskiy, Leyuan Sheng, Dong-Yan Huang

Research output: Working paper

Abstract

In speech synthesis and speech enhancement systems, melspectrograms need to be precise in acoustic representations. However, the generated spectrograms are over-smooth, that could not produce high quality synthesized speech. Inspired by image-to-image translation, we address this problem by using a learning-based post filter combining Pix2PixHD and ResUnet to reconstruct the mel-spectrograms together with super-resolution. From the resulting super-resolution spectrogram networks, we can generate enhanced spectrograms to produce high quality synthesized speech. Our proposed model achieves improved mean opinion scores (MOS) of 3.71 and 4.01 over baseline results of 3.29 and 3.84, while using vocoder Griffin-Lim and WaveNet, respectively.
Original languageEnglish
Number of pages6
Publication statusPublished - 3 Dec 2019

Fingerprint

Dive into the research topics of 'High-quality Speech Synthesis Using Super-resolution Mel-Spectrogram'. Together they form a unique fingerprint.

Cite this