Avocodo: Generative Adversarial Network for Artifact-free Vocoder
By Taejun Bak, Hanbin Bae, Jinhyeok Yang, Jaesung Bae, Young-Sun Joo. 2022
45 citations recorded by the source corpus.
Neural vocoders based on the generative adversarial neural network (GAN) have been widely used due to their fast inference speed and lightweight networks while generating high-quality speech waveforms. Since the perceptually important speech components are primarily concentrated in the low-frequency bands, most GAN-based vocoders perform multi-scale analysis that evaluates downsampled speech waveforms. This multi-scale analysis helps the generator improve speech intelligibility. However, in preliminary experiments, we discovered that the multi-scale analysis which focuses on the low-frequency bands causes unintended artifacts, e.g., aliasing and imaging artifacts, which degrade the synthesized speech waveform quality. Therefore, in this paper, we investigate the relationship between these artifacts and GAN-based vocoders and propose a GAN-based vocoder, called Avocodo, that allows the synthesis of high-fidelity speech with reduced artifacts. We introduce two kinds of discriminators to evaluate speech waveforms in various perspectives: a collaborative multi-band discriminator and a sub-band discriminator. We also utilize a pseudo quadrature mirror filter bank to obtain downsampled multi-band speech waveforms while avoiding aliasing. According to experimental results, Avocodo outperforms baseline GAN-based vocoders, both objectively and subjectively, while reproducing speech with fewer artifacts.
Subfields: Artificial Intelligence, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Signal Processing
Citations in the corpus
- Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis (2023, background): “However, this design is known to be susceptible to aliasing artifacts, and there are works suggesting more specialized modules for both the discriminator (Bak et al., 2022) and generator (Lee et al.”
- Improve GAN-based Neural Vocoder using Truncated Pointwise Relativistic Least Square GAN (2022, methodology): “Avocodo[1] proposes two kinds of discriminators in the multi-band domain, similar to MRD, attempting to eliminate some artifacts in both speech and singing voice synthesis tasks, which resulting in a neural vocoder with strong generalization ability. iSTFTNet[8] proposes to generate waveforms from t”