activity
20222024
most citedHiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation

2 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing eess.ASShow all

2 papers · 1 filter

eess.AS2024

InstructSing: High-Fidelity Singing Voice Generation via Instructing Yourself

Chang Zeng, Chunhui Wang, Xiaoxiao Miao +3

It is challenging to accelerate the training process while ensuring both high-quality generated voices and acceptable inference speed. In this paper, we propose a novel neural voco…

eess.AS2022★ 2 cited

HiFi-WaveGAN: Generative Adversarial Network with Auxiliary Spectrogram-Phase Loss for High-Fidelity Singing Voice Generation

Chunhui Wang, Chang Zeng, Jun Chen +1

Entertainment-oriented singing voice synthesis (SVS) requires a vocoder to generate high-fidelity (e.g. 48kHz) audio. However, most text-to-speech (TTS) vocoders cannot reconstruct…