상세정보
학술대회
A Pitch-Synchronous Speech Analysis and Synthesis Method for DNN-SPSS System
- 발행일
- 201610
- 출처
- International Conference on Digital Signal Processing (DSP) 2016, pp.408-411
- 협약과제
- 16MR3200, 시청각장애인 방송접근권 향상을 위한 디지털자막·음성해설 서비스 기술 개발, 안충현
- 초록
- This paper proposes a pitch-synchronous deep neural network (DNN)-based statistical parametric speech synthesis (SPSS) system. The pitch-synchronous frames defined by the locations of glottal closure instants (GCIs) are used to extract speech parameters, which significantly reduce coupling effects between vocal tract and excitation signals. As a result, the distribution of spectral parameters within the same context of phonetic classes becomes more uniform, which improves a model trainability especially for a small-scaled DNN framework. Although the effectiveness of pitch-synchronous approach has been proven in other applications, it is not trivial to integrate the method into the typical DNN-based SPSS systems that have regularized structures, i.e. fixed frame rate and fixed dimension of features. In this paper, we design a new DNN-based SPSS system that pitch-synchronously trains and generates speech parameters. Objective and subjective test results verify the superiority of the proposed system compared to the conventional approach.
- KSP 제안 키워드
- Coupling effects, Deep neural network(DNN), Excitation signals, Fixed dimension, Frame rate, Speech analysis, Statistical Parametric Speech Synthesis(SPSS), Subjective test, Synchronous approach, Synthesis Method, analysis and synthesis