English

Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms

Sound 2022-06-28 v1 Machine Learning Audio and Speech Processing

Abstract

We describe our approach for the generative emotional vocal burst task (ExVo Generate) of the ICML Expressive Vocalizations Competition. We train a conditional StyleGAN2 architecture on mel-spectrograms of preprocessed versions of the audio samples. The mel-spectrograms generated by the model are then inverted back to the audio domain. As a result, our generated samples substantially improve upon the baseline provided by the competition from a qualitative and quantitative perspective for all emotions. More precisely, even for our worst-performing emotion (awe), we obtain an FAD of 1.76 compared to the baseline of 4.81 (as a reference, the FAD between the train/validation sets for awe is 0.776).

Cite

@article{arxiv.2206.12563,
  title  = {Generating Diverse Vocal Bursts with StyleGAN2 and MEL-Spectrograms},
  author = {Marco Jiralerspong and Gauthier Gidel},
  journal= {arXiv preprint arXiv:2206.12563},
  year   = {2022}
}

Comments

To be published at the ICML Expressive Vocalizations Workshop and Competition (ExVo Generate) held in conjunction with the 39th International Conference on Machine Learning

R2 v1 2026-06-24T12:03:41.089Z