| Paper: | SLP-P10.8 | ||
| Session: | Speech Synthesis II | ||
| Time: | Wednesday, May 17, 14:00 - 16:00 | ||
| Presentation: | Poster | ||
| Topic: | Speech and Spoken Language Processing: Prosody, Emotional, and Expressive Synthesis | ||
| Title: | Quantitative Target Approximation Model: Simulating Underlying Mechanisms of Tones and Intonations | ||
| Authors: | Santitham Prom-on, Yi Xu, University College London, United Kingdom; Bundit Thipakorn, King Mongkut's University of Technology Thonburi, Thailand | ||
| Abstract: | This paper proposes a quantitative target approximation (qTA) model for simulating tone and intonation. Based on two theoretical models: the target approximation model [13] and the PENTA model [11], the qTA model additionally incorporates several assumptions related to the underlying articulatory mechanisms, including (1) F0 production can be represented by a second-order overdamped system, and (2) the system is controlled by a time-delayed feedback loop to sequentially approximates underlying pitch targets. We tested the model with the dataset from [14]. Two experiments were conducted to validate the model and to study the effect of tone, position, and focus. The results were satisfactory in term of the error rate and correlation. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012