一种有效的语音变调算法研究

An Efficient Algorithm for Pitch-scale Modification

在语音信号处理中,语音变调技术是一项非常重要的内容。目前采用较多的算法为同步叠加固定合成算法(Synchronized Overlap-Add Fixed Synthesis,SOLA-FS)。该算法简单,但存在着变调范围小、音质差等弊端。为了改善变调语音的音质,提高语音清晰度,在SOLA-FS算法的基础上,提出了一种不改变原语音的采样率,而在播放时采用设定的采样率播放的方法实现语音变调。实验结果表明,相对于SOLA-FS算法,新方法明显地改善了语音在连接点处相位不连续的问题,具有更好的变调效果。

Pitch-scale modification technology is an important researching topic in speech signal processing. As all of the algorithms concerned, SOLA-FS is widely used for its sim- plicity. But there are also some disadvantages, for example, small pitch-scale modification range, poor quality, and so on. In order to improve the pitch-scale modification range and quality, a new algorithm is proposed, on the basis of SOLA-FS, which does not change the original speech sampling rate during speech wave transform. But the modified speech will be played with a new sampling rate. Experimental results show that the new method improves the phase discontinuity at connection point obviously and gives a better tone effect compared with the SOLA-FS algorithm.