PyTorch implementation of the DeepTalk model described in DeepTalk: Vocal Style Encoding for Speaker Recognition and Speech Synthesis by A. Chowdhury, A. Ross, and P. David in IEEE International Conference on Acoustics, Speech and Signal Processing 2021 (ICASSP-2021). The code is applied to the domain of emotion recognition to investigate correlations between speaker identity and emotion state.
Morgan Sandler and Arun Ross, Is Style All You Need? Dependencies Between Emotion and GST-based Speaker Recognition, 2022.
- arXiv: https://arxiv.org/