Improved Parallel Wavegan Vocoder with Perceptually Weighted Spectrogram Loss
By Eunwoo Song, Ryuichi Yamamoto, Min-Jae Hwang, Jin-Seob Kim, Ohsung Kwon, Jae-Min Kim. 2021
18 citations recorded by the source corpus.
This paper proposes a spectral-domain perceptual weighting technique for Parallel WaveGAN-based text-to-speech (TTS) systems. The recently proposed Parallel WaveGAN vocoder successfully generates waveform sequences using a fast non-autoregressive WaveNet model. By employing multi-resolution short-time Fourier transform (MR-STFT) criteria with a generative adversarial network, the light-weight convolutional networks can be effectively trained without any distillation process. To further improve the vocoding performance, we propose the application of frequency-dependent weighting to the MR-STFT loss function. The proposed method penalizes perceptually-sensitive errors in the frequency domain; thus, the model is optimized toward reducing auditory noise in the synthesized speech. Subjective listening test results demonstrate that our proposed method achieves 4.21 and 4.26 TTS mean opinion scores for female and male Korean speakers, respectively.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
In Signal Processing
Citations in the corpus
- A Survey on Neural Speech Synthesis (2021, background): “A lot of vocoders leverage GAN to ensure the audio generation quality, including WaveGAN [66], GAN-TTS [23], MelGAN [174], Parallel WaveGAN [396], HiFi-GAN [170], and other GAN-based vocoders [395, 385, 306, 410, 366, 134].”
- GAN Vocoder: Multi-Resolution Discriminator Is All You Need (2021, background): “Parallel WaveGAN (PWGAN) and its enhanced variation that applies a perceptually weighted mask to spectrogram when computing losses [15] generate audio by taking a Gaussian noise.”