The principle and testing method of voice quality assessment algorithm is researched. 本文的主要内容包括:1.对语音质量评估(VQA)算法的原理和测试方案进行研究。
It combines domestic and international voice quality assessment as well as neural network, a set of output-based MOS evaluation method, combined with the Changde mobile research and development projects. 结合国内外对语音质量评估(VQA)以及神经网络的研究,提出了一套基于输出的MOS评价方法,并结合常德移动的实际情况进行了项目研发。
Through research of ITU-T voice quality assessment algorithm, the scope and accuracy level of algorithm is understood and the appropriate assessment method is selected. 通过对ITU-T的语音质量评估(VQA)算法建议的分析,了解其评估算法的适用范围和精确程度,从而选择出合适的评估方法。
The assessment of voice quality by Vocal Assessment took an important role in the voice therapy, and Jitter, shimmer and NNE were tested to be effective parameters for voice quality. 结论①音质评估在嗓音治疗过程中起着非常重要的作用,其中Jitter,Shimmer,NNE被证明是衡量嗓音音质的3个有效参数;②患儿接受的嗓音矫治方法是有效的。