Conditional Spoken Digit Generation with StyleGAN

By Kasperi Palkama, Lauri Juvela, Alexander Ilin. 2020

11 citations recorded by the source corpus.

This paper adapts a StyleGAN model for speech generation with minimal or no conditioning on text. StyleGAN is a multi-scale convolutional GAN capable of hierarchically capturing data structure and latent variation on multiple spatial (or temporal) levels. The model has previously achieved impressive results on facial image generation, and it is appealing to audio applications due to similar multi-level structures present in the data. In this paper, we train a StyleGAN to generate mel-frequency spectrograms on the Speech Commands dataset, which contains spoken digits uttered by multiple speakers in varying acoustic conditions. In a conditional setting our model is conditioned on the digit identity, while learning the remaining data variation remains an unsupervised task. We compare our model to the current unsupervised state-of-the-art speech synthesis GAN architecture, the WaveGAN, and show that the proposed model outperforms according to numerical measures and subjective evaluation by listening tests.

Subfields: Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

1. Wei Ping
2. Zhifeng Kong
3. Bryan Catanzaro
4. Kexin Zhao
5. Jiaji Huang
6. Jonathan Ho
7. Xu Tan
8. Arash Vahdat

Citations in the corpus

• DiffWave: A Versatile Diffusion Model for Audio Synthesis (2020, background): “, 200×) than waveform (Vasquez & Lewis, 2019; Engel et al., 2019; Palkama et al., 2020).”