基于统计声学模型的单元挑选语音合成算法  

Statistical Acoustic Model Based Unit Selection Algorithm for Speech Synthesis

作　　者：凌震华[1] 王仁华[1] 

机构地区：[1]中国科学技术大学电子工程与信息科学系讯飞语音实验室,合肥230027

出　　处：《模式识别与人工智能》2008年第3期280-284,共5页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.60475015);国家863计划项目(No.AA2100060005)资助

摘　　要：提出一种基于统计声学模型的单元挑选语音合成算法.在模型训练阶段,首先提取语料库中语音数据的频谱、基频等声学参数,结合语料库中的音段和韵律标注来估计各上下文相关音素对应的统计声学模型,使用的模型结构为隐马尔柯夫模型.在合成阶段,以使目标合成句对应的声学模型具有最大的似然值输出为准则,来进行最佳合成单元的挑选,最后通过平滑连接各备选单元波形来生成合成语音.以此算法为基础,构建一个以声韵母为基本拼接单元的中文语音合成系统,并通过测听实验证明此算法相对传统算法在提高合成语音自然度上的有效性.A statistical acoustic model based unit selection algorithm for speech synthesis is proposed. During training stage, the acoustic models for contextual dependent phonemes are built up by using acoustic features extracted from the training data, such as spectral parameters, F0, and segmental and prosodic labels in the corpus. The hidden Markov model （HMM） is adopted as the model structure. During synthesis stage, the optimal phoneme unit sequence is searched in the speech corpus by maximizing the probabilistic likelihood between its acoustic features and the sentence HMM constructed with the contextual information of input text. Finally, the waveforms of the selected candidate units are concatenated and smoothed to produce the synthesized speech. Based on the proposed method, a Chinese speech synthesis system using initials and finals as the basic concatenation units is constructed. Results of listening test prove that the proposed method can achieve better naturalness of synthesized speech compared to the conventional method.

关 键 词：语音合成 单元挑选 统计声学模型 隐马尔柯夫模型(HMM) 最大似然准则 

分 类 号：TN912.33[电子电信—通信与信息系统]