GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion Models
By Matthew Baas, Herman Kamper. 2022
10 citations recorded by the source corpus.
We propose AudioStyleGAN (ASGAN), a new generative adversarial network (GAN) for unconditional speech synthesis. As in the StyleGAN family of image synthesis models, ASGAN maps sampled noise to a disentangled latent vector which is then mapped to a sequence of audio features so that signal aliasing is suppressed at every layer. To successfully train ASGAN, we introduce a number of new techniques, including a modification to adaptive discriminator augmentation to probabilistically skip discriminator updates. ASGAN achieves state-of-the-art results in unconditional speech synthesis on the Google Speech Commands dataset. It is also substantially faster than the top-performing diffusion models. Through a design that encourages disentanglement, ASGAN is able to perform voice conversion and speech editing without being explicitly trained to do so. ASGAN demonstrates that GANs are still highly competitive with diffusion models. Code, models, samples: https://github.com/RF5/simple-asgan/.
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
- Cong Han
- Nima Mesgarani
- Gavin Mischler
- Vinay S. Raghavan
- Yi Luo
- John R. Hershey
- Jonathan Le Roux
- Yossi Adi
In Signal Processing
- Cong Han
- Gavin Mischler
- Vinay S. Raghavan
- Nima Mesgarani
- Yi Luo
- Jonathan Le Roux
- Yossi Adi
- Zhuo Chen
Citations in the corpus
- StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models (2023, background): “Furthermore, recent works suggest that state-of-the-art GAN-based models still perform better than diffusion models in speech synthesis [26, 33].”