GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model

arXiv:2402.15516v1 Announce Type: cross
Abstract: Diffusion models are receiving a growing interest for a variety of signal generation tasks such as speech or music synthesis. WaveGrad, for example, is a successful diffusion model that conditionally uses the mel spectrogram to guide a diffusion process for the generation of high-fidelity audio. However, such models face important challenges concerning the noise diffusion process for training and inference, and they have difficulty generating high-quality speech for speakers that were not seen during training. …

abstract arxiv audio cs.lg cs.sd diffusion diffusion model diffusion models eess.as eess.sp example fidelity griffin guide music music synthesis process signal spectrogram speech synthesis tasks type