实验结果表明：与说话人有关的孤立词识别率达到98%。
The experimental results show that the depended speaker speech recognition rate is 98%.
音频流识别实验表明，三音素HMM模型词识别率明显高于单音素HMM；
Audio experiment results show that tri-phone HMM has higher word recognition rates than monophone HMM.
将弹性音节拼接与具有较高性能的基于特征空间轨迹匹配的关键词检测相结合构建识别系统，实验结果表明该系统具有相当高的识别率。
This paper proposes a keyword spotting method based on adjustable syllable joining and feature space trace matching, experiments show that this method has high performance and efficiency.
实验结果表明，本方法对应力影响下的变异语音具有良好识别效果，对15个词的小词表，系统平均识别率达到98.3%，与正常语音的识别率基本相当。
The experiments showed that for a small vocabulary including 15 words, the method obtained the average recognition rate of 98.3%, which almost equal to the rate in normal environment.
实验结果表明，本方法对应力影响下的变异语音具有良好识别效果，对15个词的小词表，系统平均识别率达到98.3%，与正常语音的识别率基本相当。
The experiments showed that for a small vocabulary including 15 words, the method obtained the average recognition rate of 98.3%, which almost equal to the rate in normal environment.
应用推荐