Abstract
In this letter, we propose a high-quality emotional speech synthesis system, using emotional vector space, i.e., the weighted sum of global style tokens (GSTs). Our previous research verified the feasibility of GST-based emotional speech synthesis in an end-to-end text-to-speech synthesis framework. However, selecting appropriate reference audio (RA) signals to extract emotion embedding vectors to the specific types of target emotions remains problematic. To ameliorate the selection problem, we propose an effective way of generating emotion embedding vectors by utilizing the trained GSTs. By assuming that the trained GSTs represent an emotional vector space, we first investigate the distribution of all the training samples depending on the type of each emotion. We then regard the centroid of the distribution as an emotion-specific weighting value, which effectively controls the expressiveness of synthesized speech, even without using the RA for guidance, as it did before. Finally, we confirm that the proposed controlled weight-based method is superior to the conventional emotion label-based methods in terms of perceptual quality and emotion classification accuracy.
Original language | English |
---|---|
Article number | 8778667 |
Pages (from-to) | 1383-1387 |
Number of pages | 5 |
Journal | IEEE Signal Processing Letters |
Volume | 26 |
Issue number | 9 |
DOIs | |
Publication status | Published - 2019 Sep |
Bibliographical note
Funding Information:Manuscript received May 26, 2019; revised July 9, 2019; accepted July 13, 2019. Date of publication July 29, 2019; date of current version August 8, 2019. This work was supported by Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (2019-0-00447, Development of emotional expression service to support hearing/visually impaired). The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Odette Scharenborg. (Corresponding author: Hong-Goo Kang.) O. Kwon and H.-G. Kang are with the Department of Electrical and Electronics, Yonsei University, Seoul 03722, South Korea (e-mail: osungv@dsp. yonsei.ac.kr; hgkang@yonsei.ac.kr).
Publisher Copyright:
© 2019 IEEE.
All Science Journal Classification (ASJC) codes
- Signal Processing
- Applied Mathematics
- Electrical and Electronic Engineering