This paper proposes providing automatic feedback to support public speech training. For the first time, speech feedback is provided on a visual dashboard including not only the transcription and pitch information, but also emotion information. A method is proposed to perform emotion classification using state-of-the-art convolutional neural networks (CNNs). Moreover, this approach can be used for speech analysis purposes. A case study exploring pitch in Japanese speech is presented in this paper.
Wynn, A. T., Wang, J., Umezawa, K., & Cristea, A. I. (2022). An AI-Based Feedback Visualisation System for Speech Training. In M. Mercedes Rodrigo, N. Matsuda, A. I. Cristea, & V. Dimitrova (Eds.), Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners’ and Doctoral Consortium (510-514). Springer Verlag. https://doi.org/10.1007/978-3-031-11647-6_104