DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation

arXiv:2310.01381v3 Announce Type: replace-cross
Abstract: Diffusion models have recently been shown to be relevant for high-quality speech generation. Most work has been focused on generating spectrograms, and as such, they further require a subsequent model to convert the spectrogram to a waveform (i.e., a vocoder). This work proposes a diffusion probabilistic end-to-end model for generating a raw speech waveform. The proposed model is autoregressive, generating overlapping frames sequentially, where each frame is conditioned on a portion of the previously generated …

abstract arxiv autoregressive model cs.cl cs.sd denoising diffusion diffusion models eess.as quality raw spectrogram speech speech generation type work