说话人自适应技术在维吾尔语语音识别中的应用研究

Speaker Adaptation Technology in Uyghur Continuous Speech Recognition

该文针对维吾尔语说话人之间的发音差异会在一定程度上影响维吾尔语语音识别系统的性能这一情况研究了说话人自适应技术,将目前较为常用的MLLR和MAP以及MLLR和MAP相结合的自适应方法应用于维吾尔语连续语音识别的声学模型训练中,并用这三种方法自适应后的声学模型分别在测试集上进行识别实验。实验结果表明MLLR、MAP以及MAP+MLLR自适应方法使基线识别系统的单词错误识别率分别降低了0.6%、2.34%和2.57%。

Researches show that pronunciation differences between the speakers can cause serious effects on the Uy- ghur speech recognition system. Focused on the speaker adaptation technology,this paper applies MLLR, MAP and MLLR＋ MAP methods to the training of acoustic models of Uyghur Continuous Speech Recognition system. Exper- imental results show that with the three speaker adaptation methods,the word error rate is reduced by 0. 6%,2. 34% and 2.57%, respectively.