Articulatory Synthesis in a Vowel-to-Vowel Imitation Task
  • View Times: 68
  • |
  • Release Date: 2023-04-14
  • speech modeling
  • reinforcement learning
  • speech synthesis
Video Introduction

This video is adapted from 10.3390/s23073437

Articulatory synthesis is one of the approaches used for modeling human speech production. To improve the sample efficiency of the learning, researchers trained the model of speech production dynamics simultaneously with the policy. The policy was trained in a supervised way using predictions of the model of speech production dynamics. To stabilize the training, early stopping was incorporated into the algorithm. Additionally, researchers extracted acoustic features using an acoustic word embedding (AWE) model.

Full Transcript
1000/1000

Confirm

Are you sure to Delete?
Cite
If you have any further questions, please contact Encyclopedia Editorial Office.
Lech, M.; Shitov, D.; Pirogova, E.; Wysocki, T.A. Articulatory Synthesis in a Vowel-to-Vowel Imitation Task. Encyclopedia. Available online: https://encyclopedia.pub/video/video_detail/712 (accessed on 24 April 2024).
Lech M, Shitov D, Pirogova E, Wysocki TA. Articulatory Synthesis in a Vowel-to-Vowel Imitation Task. Encyclopedia. Available at: https://encyclopedia.pub/video/video_detail/712. Accessed April 24, 2024.
Lech, Margaret, Denis Shitov, Elena Pirogova, Tadeusz A. Wysocki. "Articulatory Synthesis in a Vowel-to-Vowel Imitation Task" Encyclopedia, https://encyclopedia.pub/video/video_detail/712 (accessed April 24, 2024).
Lech, M., Shitov, D., Pirogova, E., & Wysocki, T.A. (2023, April 14). Articulatory Synthesis in a Vowel-to-Vowel Imitation Task. In Encyclopedia. https://encyclopedia.pub/video/video_detail/712
Lech, Margaret, et al. "Articulatory Synthesis in a Vowel-to-Vowel Imitation Task." Encyclopedia. Web. 14 April, 2023.