基于音素混淆网络的蒙古语语音关键词检测方法的研究

Research on Mongolian Spoken Term Detection Based on Phoneme Confusion Network

蒙古语语音识别系统的词表很难覆盖所有的蒙古文单词,并且随着社会的发展,蒙古文的新词和外来词也越来越多。为了解决蒙古语语音关键词检测系统中的集外词检测问题,该文提出了基于音素混淆网络的蒙古语语音关键词检测方法,并采用音素混淆矩阵改进了关键词的置信度计算方法。实验结果表明,基于音素混淆网络的蒙古语语音关键词检测方法可以较好地解决集外词的检测问题。蒙古语语音关键词检测系统采用改进的置信度计算方法后精确率提高了6%,召回率提高了2.69%,性能得到明显的提升。

To deal with Out-of-Vocabulary detection on Mongolian spoken term detection system, this paper propo ses a Mongolian spoken term detection method based on phoneme confusion network. The Confidence Measure is im- proved by incorporating phoneme confusion matrix. Experimental. results show that our method obtains a satisfying performance in the task of Mongolian Out-of-Vocabulary detection, with 6% improvement in precision rate and 2. 69% in recall rate.