Framewise Wavegan: High Speed Adversarial Vocoder In Time Domain With Very Low Computational Complexity

Abstract

GAN vocoders are currently one of the state-of-the-art methods for building high-quality neural waveform generative models. However, most of their architectures require dozens of billion floating-point operations per second (GFLOPS) to generate speech waveforms in samplewise manner. This makes GAN vocoders still challenging to run on normal CPUs without accelerators or parallel computers. In this work, we propose a new architecture for GAN vocoders that mainly depends on recurrent and fully-connected networks to directly generate the time domain signal in framewise manner. This results in considerable reduction of the computational cost and enables very fast generation on both GPUs and low-complexity CPUs. Experimental results show that our Framewise WaveGAN vocoder achieves significantly higher quality than auto-regressive maximum-likelihood vocoders such as LPCNet at a very low complexity of 1.2 GFLOPS. This makes GAN vocoders more practical on edge and low-power devices.

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keymustafa2022framewise

Related papers

• Vocgan: A High-fidelity Real-time Vocoder With A Hierarchically-nested Adversarial Network (2020)12.54
• Very Low Complexity Speech Synthesis Using Framewise Autoregressive GAN (FARGAN) With Pitch Prediction (2024)6.34
• Vocos: Closing The Gap Between Time-domain And Fourier-based Neural Vocoders For High-quality Audio Synthesis (2023)6.10
• TFGAN: Time And Frequency Domain Based Generative Adversarial Network For High-fidelity Speech Synthesis (2020)0.00
• Parallel Wavegan: A Fast Waveform Generation Model Based On Generative Adversarial Networks With Multi-resolution Spectrogram (2019)0.00
• Analysis By Adversarial Synthesis -- A Novel Approach For Speech Vocoding (2019)3.58
• Bigvgan: A Universal Neural Vocoder With Large-scale Training (2022)6.17
• Wavefit: An Iterative And Non-autoregressive Neural Vocoder Based On Fixed-point Iteration (2022)9.41