Deep Representation Learning for Affective Speech Signal Analysis and Processing: Preventing unwanted signal disparities
Published in IEEE Signal Processing Magazine, 2021
Recommended citation: Lee, C. C., Sridhar, K., Li, J. L., Lin, W. C., Su, B. H., & Busso, C. (2021). "Deep Representation Learning for Affective Speech Signal Analysis and Processing: Preventing unwanted signal disparities." IEEE Signal Processing Magazine, 38(6), 22-38. 1(1). https://ieeexplore.ieee.org/abstract/document/9591505
This paper is providing a tutorial of the current techniques applied to speech emotion recognition (SER), which is divided into three major components including Robustness, Generalization, and Usability. In this paper, readers could quickly follow up and conduct the hands-on experiment with the provided example guiding.
Recommended citation: Lee, C. C., Sridhar, K., Li, J. L., Lin, W. C., Su, B. H., & Busso, C. (2021). “Deep Representation Learning for Affective Speech Signal Analysis and Processing: Preventing unwanted signal disparities.” IEEE Signal Processing Magazine, 38(6), 22-38. 1(1).