Modification Of Velvet Noise For Speech Waveform Generation By Using Vocoder-Based Speech Synthesizer
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS(2019)
摘要
This paper introduces a new noise generation algorithm for vocoder-based speech waveform generation. White noise is generally used for generating an aperiodic component. Since short-term white noise includes a zero-frequency component (ZFC) and inaudible components below 20 Hz, they are reduced in advance when synthesizing. We propose a new noise generation algorithm based on that for velvet noise to overcome the problem. The objective evaluation demonstrated that the proposed algorithm can reduce the unwanted components.
更多查看译文
关键词
noise generation, white noise, velvet noise, zero-frequency component, speech analysis/synthesis
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络