摘要
针对已有测试系统存在易受噪声干扰,测试精度低的难题,为了提高测试效果,设计了一种基于复杂噪声干扰的英语口语测试系统。首先分析了当前研究进展,并采集测试信号,对信号进行去噪处理,抑制噪声的干扰,然后从信号提取特征向量,并引入隐马尔可夫模型建立信号分类器,得到测试结果。最后进行了系统性能测试,结果表明,本系统可以有效消除噪声对测试结果的干扰,获得了理想的英语口语测试结果。
For existing test system is easy to be disturbed by noise and the test accuracy is low, in order to improve the test effect, an oral English test system based on complex noise interference is designed. Firstly, this paper analyzes the current research progress, collects the oral English test signals, denoises the signals and suppresses the interference of noise, then extracts the feature vector from the signals, introduces the hidden Markov model to establish the signal classifier, and obtains the test results. Finally, the system performance test is carried out. The results show that the system in this paper can effectively eliminate the interference of noise on the test results, the ideal oral English test results are obtained.
作者
霍小静
HUO Xiao-jing(Xi'an Peihua University,Xi'an 710125 China)
出处
《自动化技术与应用》
2022年第10期159-162,共4页
Techniques of Automation and Applications
基金
西安培华学院2019年度校级课堂教学模式创新专项(PHJM1904)。
关键词
复杂噪声
英语口语
测试系统
语音特征
complex noise
spoken English
test system
speech features