Design of a Mandarin Spoken Dialogue System Using Tacotron2-based Speech Synthesis with Dialogist-aware System-speaking-style Switching
Sensors and Materials · 2026-03-23 · 38 (3) · 1447
DOI: 10.18494/sam5946 ↗At a glance
Journal article in Sensors and Materials, published on 2026-03-23. Written by Ing-Jr Ding and 3 co-authors.
Abstract (original language)
With the recognized dialogist, the fine-tuned adaptation Tacotron2 model matched to this dialogist will then be used to perform speech synthesis. To evaluate the naturalness of the synthetic speech, various signal analysis evaluation metrics, including Mel-cepstral distortion (MCD), linear prediction code distortion (LPCD), and peak signal-to-noise ratio (PSNR), are also carried out in this work to investigate the effectiveness and compare the accuracy by the human-decision mean opinion score (MOS) approach.
Cite
APA
Ding, I., Chen, P., Li, X., & Yan, Y. (2026). Design of a Mandarin Spoken Dialogue System Using Tacotron2-based Speech Synthesis with Dialogist-aware System-speaking-style Switching. Sensors and Materials, 38(3), 1447. https://doi.org/10.18494/sam5946
Vancouver
Ding I, Chen P, Li X, Yan Y. Design of a Mandarin Spoken Dialogue System Using Tacotron2-based Speech Synthesis with Dialogist-aware System-speaking-style Switching. Sensors and Materials. 2026;38(3):1447. doi:10.18494/sam5946
BibTeX
@article{Ding2026,
author = {Ding, Ing-Jr and Chen, Po-Jung and Li, Xin-Bau and Yan, Yih-Her},
title = {Design of a Mandarin Spoken Dialogue System Using Tacotron2-based Speech Synthesis with Dialogist-aware System-speaking-style Switching},
journal = {Sensors and Materials},
year = {2026},
volume = {38},
number = {3},
pages = {1447},
doi = {10.18494/sam5946}
}
EUVIMED