Humans can guess how someone on the other end of a phone call is feeling based on how they speak as well as what they say. Speech emotion recognition is the artificial intelligence version of this ability. Seeking to address the issue of channel alignment in downstream speech emotion recognition applications, a research group at East China Normal University in Shanghai developed a temporal shift module that outperforms state-of-the-art methods in fine-tuning and feature-extraction scenarios.
This article was originally published on this website.
