Parallel WaveNet: Fast High-Fidelity Speech Synthesis

The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on sequential generation of one audio sample at a time, it is poorly suited to today's massively parallel computers, and therefore hard to deploy in a real-time production setting. This paper introduces Probability Density Distillation, a new method for training a parallel feed-forward network from a trained WaveNet with no significant difference in quality. The resulting system is capable of generating high-fidelity speech samples at more than 20 times faster than real-time, and is deployed online by Google Assistant, including serving multiple English and Japanese voices.

[1]  Boris Polyak,et al.  Acceleration of stochastic approximation by averaging , 1992 .

[2]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[3]  Hugo Larochelle,et al.  The Neural Autoregressive Distribution Estimator , 2011, AISTATS.

[4]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[5]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[6]  Alex Graves,et al.  Generating Sequences With Recurrent Neural Networks , 2013, ArXiv.

[7]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[8]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[9]  Shakir Mohamed,et al.  Variational Inference with Normalizing Flows , 2015, ICML.

[10]  Hugo Larochelle,et al.  MADE: Masked Autoencoder for Distribution Estimation , 2015, ICML.

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2015, ICLR.

[12]  Yoshua Bengio,et al.  NICE: Non-linear Independent Components Estimation , 2014, ICLR.

[13]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Matthias Bethge,et al.  Generative Image Modeling Using Spatial LSTMs , 2015, NIPS.

[15]  Leon A. Gatys,et al.  A Neural Algorithm of Artistic Style , 2015, ArXiv.

[16]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

[17]  Koray Kavukcuoglu,et al.  Pixel Recurrent Neural Networks , 2016, ICML.

[18]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[19]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[20]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[21]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[22]  Thomas S. Huang,et al.  Fast Wavenet Generation Algorithm , 2016, ArXiv.

[23]  Samy Bengio,et al.  Density estimation using Real NVP , 2017, ICLR.

[24]  Lucas Theis,et al.  Amortised MAP Inference for Image Super-resolution , 2016, ICLR.

[25]  Iain Murray,et al.  Masked Autoregressive Flow for Density Estimation , 2017, NIPS.

[26]  Pieter Abbeel,et al.  Variational Lossy Autoencoder , 2016, ICLR.

[27]  Xi Chen,et al.  PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications , 2017, ICLR.

[28]  Max Welling,et al.  Improved Variational Inference with Inverse Autoregressive Flow , 2016, NIPS 2016.

[29]  Alex Graves,et al.  Video Pixel Networks , 2016, ICML.

[30]  Victor O. K. Li,et al.  Non-Autoregressive Neural Machine Translation , 2017, ICLR.