摘要
为减少噪声环境对评估性能的影响,该文将PNCC参数引入普通话发音评估。结果表明,其评分相关性在普通话测试实录音数据库上较传统MFCC参数提高了6.6%。在此基础上,对汉语声学模型拆分方法进行了研究,提出将声母介音+韵母模型拆分方法应用到发音评估中。使用这种拆分方式的评估系统总错误率降低5.6%,专家打分相关性则提高了0.056。该文还对模型最佳状态数的选取进行讨论,并提出模型状态数混合和不同配置综合评分两种混合评分方案,在相关性上较同等条件下3状态模型分别提高了0.021和0.017。
In this paper, PNCC(Power-Normalized Cepstral Coefficients) is introduced into Mandarin pronunciation evaluation system for reducing the impact of background noise. The result shows that the score correlation based on PNCC has been increased by 6.6% compared with classical MFCC. Then, different initial-final acoustic model structures for Chinese syllables are investigated on Mandarin pronunciation evaluation. An initial-medial and final (IMF) modeling is applied, resulting 5.6% reduction of the error rate and an increase of 0. 056 score correlation. Finally, the number of states in HMM model is discussed for pronunciation scoring, and some mixed score compu- ting schemes based on either models or scores are proposed. Test results show the score correlation with the experts has been increased by 0. 021 and 0. 017 respectively.
出处
《中文信息学报》
CSCD
北大核心
2013年第3期48-55,共8页
Journal of Chinese Information Processing
基金
2010年北京师范大学自主科研基金项目资助
2010年北京师范大学教学建设与改革项目资助
关键词
发音评估
PNCC
模型拆分
HMM状态数
mandarin pronunciation evaluation
PNCC~ initial-medial and final
HMM states