@inproceedings{agritsenko2020a,
author = {A. Gritsenko, Alexey and Salimans, Tim and van den Berg, Rianne and Snoek, Jasper and Kalchbrenner, Nal},
title = {A Spectral Energy Distance for Parallel Speech Synthesis},
booktitle = {2020 Neural Information Processing Systems},
year = {2020},
month = {August},
abstract = {Speech synthesis is an important practical generative modeling problem that has seen great progress over the last few years, with likelihood-based autoregressive neural models now outperforming traditional concatenative systems. A downside of such autoregressive models is that they require executing tens of thousands of sequential operations per second of generated audio, making them ill-suited for deployment on specialized deep learning hardware. Here, we propose a new learning method that allows us to train highly parallel models of speech, without requiring access to an analytical likelihood function. Our approach is based on a generalized energy distance between the distributions of the generated and real audio. This spectral energy distance is a proper scoring rule with respect to the distribution over magnitude-spectrograms of the generated waveform audio and offers statistical consistency guarantees. The distance can be calculated from minibatches without bias, and does not involve adversarial learning, yielding a stable and consistent method for training implicit generative models. Empirically, we achieve state-of-the-art generation quality among implicit generative models, as judged by the recently-proposed cFDSD metric. When combining our method with adversarial techniques, we also improve upon the recently-proposed GAN-TTS model in terms of Mean Opinion Score as judged by trained human evaluators.},
url = {http://approjects.co.za/?big=en-us/research/publication/a-spectral-energy-distance-for-parallel-speech-synthesis/},
pages = {13062-13072},
}