S-Space College of Engineering/Engineering Practice School (공과대학/대학원) Dept. of Electrical and Computer Engineering (전기·정보공학부) Theses (Master's Degree_전기·정보공학부)
Modulation Spectrum-based Postfiltering of Synthesized Speech in the Wavelet Domain
파형요소 도메인에서의 변조 스펙트럼 기반 음성합성 후처리
- 공과대학 전기·정보공학부
- Issue Date
- 서울대학교 대학원
- Postfiltering; Modulation spectrum (MS); Discrete wavelet transform (DWT); Dual-tree complex wavelet transform (DTCWT); Hidden Markov tree (HMT)
- 학위논문 (석사)-- 서울대학교 대학원 공과대학 전기·정보공학부, 2017. 8. 김남수.
- This thesis presents a wavelet-domain measure used in postfiltering applications. Quality of HMM-based (hidden Markov model-based) parametric speech synthesis is degraded due to the over-smoothing effect, where the trajectory of generated speech parameters is smoothed out and lacks dynamics. The conventional method uses the modulation spectrum (MS) to quantify the effect of over-smoothing by measuring the spectral tilt in the MS. In order to enhance the performance, a modified version of the MS called the scaled modulation spectrum (SMS), which essentially separates the MS in different bands, is proposed and utilized in postfiltering. The performance of two types of wavelets, the discrete wavelet transform (DWT) and the dual-tree complex wavelet transform (DTCWT), are evaluated. We also extend the SMS into a hidden Markov tree (HMT) model, which represents the interdependencies of the coefficients. Experimental results show that the proposed method performs better.