Mel Spectrogram To Waveform Vocoding

via “mel-spectrogram to waveform vocoding with glow-based architecture”

text-to-speech model by undefined. 69,91,040 downloads.

Unique: Uses a glow-based invertible neural network architecture for vocoding, enabling parallel waveform generation without autoregressive decoding. This approach is faster and more stable than traditional autoregressive vocoders (WaveNet, WaveGlow) while maintaining high audio quality.

vs others: Faster inference than autoregressive vocoders (WaveNet) because it generates waveforms in parallel rather than sample-by-sample; more stable than GAN-based vocoders because it uses likelihood-based training rather than adversarial objectives; produces higher quality audio than traditional signal processing vocoders (Griffin-Lim).