English

A Neural Denoising Vocoder for Clean Waveform Generation from Noisy Mel-Spectrogram based on Amplitude and Phase Predictions

Audio and Speech Processing 2024-11-20 v1 Signal Processing

Abstract

This paper proposes a novel neural denoising vocoder that can generate clean speech waveforms from noisy mel-spectrograms. The proposed neural denoising vocoder consists of two components, i.e., a spectrum predictor and a enhancement module. The spectrum predictor first predicts the noisy amplitude and phase spectra from the input noisy mel-spectrogram, and subsequently the enhancement module recovers the clean amplitude and phase spectrum from noisy ones. Finally, clean speech waveforms are reconstructed through inverse short-time Fourier transform (iSTFT). All operations are performed at the frame-level spectral domain, with the APNet vocoder and MP-SENet speech enhancement model used as the backbones for the two components, respectively. Experimental results demonstrate that our proposed neural denoising vocoder achieves state-of-the-art performance compared to existing neural vocoders on the VoiceBank+DEMAND dataset. Additionally, despite the lack of phase information and partial amplitude information in the input mel-spectrogram, the proposed neural denoising vocoder still achieves comparable performance with the serveral advanced speech enhancement methods.

Keywords

Cite

@article{arxiv.2411.12268,
  title  = {A Neural Denoising Vocoder for Clean Waveform Generation from Noisy Mel-Spectrogram based on Amplitude and Phase Predictions},
  author = {Hui-Peng Du and Ye-Xin Lu and Yang Ai and Zhen-Hua Ling},
  journal= {arXiv preprint arXiv:2411.12268},
  year   = {2024}
}

Comments

Accepted by NCMMSC2024

R2 v1 2026-06-28T20:04:37.417Z