基于音素HMM模型语音转换

Voice Conversion Using Phoneme-dependent HMMS

通过对语音转换的研究，提出了一种把源说话人特征转换为目标说话人特征的方法。语音转换特征参数分为两类：（1）频谱特征参数；（2）基音和声调模式。分别描述信号模型和转换方法。频谱特征用基于音素的2维HMMS建模，F0轨迹用来表示基音和音调。用基音同步叠加法对基音厨期、声调和语速进行变换。

This paper presents a voice conversion method based on transformation of characteristic features of source speaker towards a target.Voice characteristic features are grouped into two main categories：（1）the spectral features at formants;（2）the pitch and intonation patterns. Signal modeling and transformation methods for each group of voice features are outlined.The spectral features at formants are modeled using a set of two-dimension phoneme-dependent HMMS.F0 contour is used for modeling the pitch and intonation patterns of speech.A PSOLA based method is employed for transformation of pitch ,intonation patterns and speaking rate.