Empirical Evaluation of Deep Learning Model Compression Techniques on the WaveNet Vocoder
This work addresses the deployment challenge of the autoregressive WaveNet vocoder for scalable text-to-speech systems, offering incremental improvements.
This paper evaluates various model compression techniques, including sparsity methods and quantization precisions, to accelerate the WaveNet vocoder. They achieved a compression ratio of up to 13.84 without losing audio fidelity compared to the baseline.
WaveNet is a state-of-the-art text-to-speech vocoder that remains challenging to deploy due to its autoregressive loop. In this work we focus on ways to accelerate the original WaveNet architecture directly, as opposed to modifying the architecture, such that the model can be deployed as part of a scalable text-to-speech system. We survey a wide variety of model compression techniques that are amenable to deployment on a range of hardware platforms. In particular, we compare different model sparsity methods and levels, and seven widely used precisions as targets for quantization; and are able to achieve models with a compression ratio of up to 13.84 without loss in audio fidelity compared to a dense, single-precision floating-point baseline. All techniques are implemented using existing open source deep learning frameworks and libraries to encourage their wider adoption.