An AI-Based Feedback Visualisation System for Speech Training

Wynn, Adam T.; Wang, Jingyun; Umezawa, Kaoru; Cristea, Alexandra I.

Abstract

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.

Citation

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

• Online Publication Date: Jul 26, 2022
• Publication Date: 2022
• Deposit Date: Aug 8, 2022
• Publicly Available Date: Jul 27, 2023
• Publisher: Springer Verlag
• Pages: 510-514
• Series Title: Lecture Notes in Computer Science
• Series Number: 13356
• Book Title: Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners’ and Doctoral Consortium
• ISBN: 978-3-031-11646-9
• DOI: https://doi.org/10.1007/978-3-031-11647-6_104
• Public URL: https://durham-repository.worktribe.com/output/1644590