Empirical Evaluation Of Deep Learning Model Compression Techniques On The Wavenet Vocoder

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydavis2020empirical

Related papers

• Deep Vocoder: Low Bit Rate Compression Of Speech With Deep Autoencoder (2019)5.24
• Collapsed Speech Segment Detection And Suppression For Wavenet Vocoder (2018)9.03
• Wasserstein GAN And Waveform Loss-based Acoustic Model Training For Multi-speaker Text-to-speech Synthesis Systems Using A Wavenet Vocoder (2018)12.61
• A Comparison Of Recent Waveform Generation And Acoustic Modeling Methods For Neural-network-based Speech Synthesis (2018)11.76
• Low Bit-rate Speech Coding With VQ-VAE And A Wavenet Decoder (2019)14.80
• Enhancing Into The Codec: Noise Robust Speech Coding With Vector-quantized Autoencoders (2021)10.21
• Model Compression For Dnn-based Speaker Verification Using Weight Quantization (2022)3.58
• One-pass Multiple Conformer And Foundation Speech Systems Compression And Quantization Using An All-in-one Neural Model (2024)0.00