模式识别与人工智能
2025年4月3日 星期四   首 页     期刊简介     编委会     投稿指南     伦理声明     联系我们                                                                English
模式识别与人工智能  2008, Vol. 21 Issue (3): 280-284    DOI:
论文与报告 最新目录| 下期目录| 过刊浏览| 高级检索 |
基于统计声学模型的单元挑选语音合成算法*
凌震华,王仁华
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
Statistical Acoustic Model Based Unit Selection Algorithm for Speech Synthesis
LING Zhen-Hua, WANG Ren-Hua
iFly Speech Laboratory, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027

全文: PDF (408 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
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.
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
凌震华
王仁华
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    
Abstract: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.
Key wordsSpeech Synthesis    Unit Selection    Statistical Acoustic Model    Hidden Markov Model (HMM)    Maximum Likelihood Criterion   
收稿日期: 2007-07-02     
ZTFLH: TN912.33  
基金资助:国家自然科学基金项目(No.60475015)、国家863计划项目(No.AA2100060005)资助
作者简介: 凌震华,男,1979年生,博士研究生,主要研究方向为语音信号处理、语音合成.E-mail:zhling@ustc.edu.王仁华,男,1943年生,教授,博士生导师,主要研究方向为数字信号处理、语音合成、语音识别.
引用本文:   
凌震华,王仁华. 基于统计声学模型的单元挑选语音合成算法*[J]. 模式识别与人工智能, 2008, 21(3): 280-284. LING Zhen-Hua, WANG Ren-Hua. Statistical Acoustic Model Based Unit Selection Algorithm for Speech Synthesis. , 2008, 21(3): 280-284.
链接本文:  
http://manu46.magtech.com.cn/Jweb_prai/CN/      或     http://manu46.magtech.com.cn/Jweb_prai/CN/Y2008/V21/I3/280
版权所有 © 《模式识别与人工智能》编辑部
地址:安微省合肥市蜀山湖路350号 电话:0551-65591176 传真:0551-65591176 Email:bjb@iim.ac.cn
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn