Sep 3, 2020 · HiFiSinger consists of a FastSpeech based acoustic model and a Parallel WaveGAN based vocoder to ensure fast training and inference and also high voice quality.

In this paper, we develop HiFiSinger, an SVS system towards high-fidelity singing voice using 48kHz sampling rate. HiFiSinger consists of a FastSpeech based ...

In this paper, we develop HiFiSinger, an SVS system towards high-fidelity singing voice using 48kHz sampling rate. HiFiSinger consists of a FastSpeech based ...

In this paper, we develop HiFiSinger, an SVS system towards high-fidelity singing voice using 48kHz sampling rate. HiFiSinger consists of a FastSpeech based ...

This code is an unofficial implementation of HiFiSinger. The algorithm is based on the following papers: Chen, J., Tan, X., Luan, J., Qin, T., & Liu, TY (2020).

In this paper, we develop HiFiSinger, an SVS system towards high-fidelity singing voice. HiFiSinger consists of a FastSpeech based acoustic model and a Parallel ...

Sep 3, 2020 · This paper introduces multi-scale adversarial training in both the acoustic model and vocoder to improve singing modeling and proposes a ...

Sep 27, 2024 · We introduce HiddenSinger, which can generate high-quality singing voice from musical score by utilizing a neural audio codec and latent diffusion models.

Sep 3, 2020 · HiFiSinger is a neural singing voice synthesis system that aims to generate high-fidelity singing voices using a 48kHz sampling rate.

To address this problem, we propose RefineGAN, a high-fidelity neural vocoder focused on the robustness, pitch and intensity accuracy, and high-speed full-band ...