상세정보
학술대회
A Study on Acoustic Parameter Selection Strategies to Improve Deep Learning-Based Speech Synthesis
- 발행일
- 201911
- 출처
- Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA-ASC) 2019, pp.618-622
- 협약과제
- 19HR4400, 시청각 장애인의 방송시청을 지원하는 감성표현 서비스 개발, 안충현
- 초록
- In this paper, we investigate the variation in the performance of a deep learning-based speech synthesis (DLSS) system based on the configuration of output acoustic parameters. Our method is mainly applicable for vocoding-based statistical parametric speech synthesis (SPSS), which has advantages in low-resource scenarios. Given the independence assumption of the source-filter model for the spectral and fundamental frequency F0 parameters, we propose a reliable network architecture for training acoustic parameters. Particularly, the F0 parameter suffers from high fluctuation and an extremely low number of dimensions. To relieve these problems, we introduce a context-window approach. Furthermore, we apply data augmentation to the proposed structure to overcome a lack of training data, which is a frequent issue with multi-speaker TTS systems. Experimental results confirm the superiority of the proposed algorithm over conventional ones in both single-speaker and multi-speaker TTS setups.
- KSP 제안 키워드
- Data Augmentation, Fundamental Frequency, Learning-based, Network Architecture, Selection strategy, Statistical Parametric Speech Synthesis(SPSS), acoustic parameters, deep learning(DL), low-resource, parameter selection, source-filter model