基于BIC与PSO的简约语音识别系统创建  

Construction of concise speech recognition systems based on BIC and PSO

作　　者：包希日莫[1] 高光来[1] 张璟[2] 

机构地区：[1]内蒙古大学计算机学院,呼和浩特010021 [2]西安理工大学计算机科学与工程学院,西安710048

出　　处：《计算机工程与应用》2013年第10期14-17,117,共5页Computer Engineering and Applications

基　　金：国家自然科学基金资助项目(No.61263037)

摘　　要：针对当前尚无建立简约高效语音识别系统标准方法的情形,提出了通过贝叶斯信息准则(Bayesian InformationCriterion,BIC)中的权衡系数折中选择系统识别率与复杂度,利用改进的粒子群优化(Particle Swarm Optimization,PSO)算法优化声学模型拓扑结构,进而创建高效简约语音识别系统的新方法。TIDigits上的实验表明,与传统方法创建的同复杂度的基线系统相比,用该方法建立的新系统句子正确率提升了7.85%,与同识别率的基线系统相比,系统复杂度降低了51.4%,说明新系统能够以较低的复杂度获得较高的识别率。Aiming at the current situation of lacking standard methods to construct efficient and concise speech recognition systems, a new method to build this kind of systems is proposed, which involves determining the relative importance of the recogni- tion performance and system complexity through the value of the regularization coefficient in Bayesian Information Criterion （BIC）and optimizing acoustic model topologies using improved Particle Swarm Optimization（PSO）algorithm. Experiments on TIDigits corpus show that the new system constructed by using this method obtains 7.85% absolute increase in sentence correct rate compared to the baseline with the same complexity and built in the conventional way, and reduces 51.4% of system complexity compared to the baseline with the same recognition rate, which indicates that the new system is capable of obtaining higher recognition rate with lower system complexity.

关 键 词：隐马尔可夫模型 语音识别 高效简约系统 声学模型拓扑结构 贝叶斯信息准则 粒群优化 

分 类 号：TN912.34[电子电信—通信与信息系统]