本文選題：發(fā)音特征　切入點：發(fā)音偏誤趨勢　出處：《北京大學學報(自然科學版)》2017年02期 　論文類型：期刊論文

【摘要】：為了提升計算機輔助發(fā)音訓練(CAPT)系統(tǒng)中發(fā)音偏誤趨勢(PET)的檢測效果,確保反饋信息的準確性與有效性,提出一種基于對數(shù)似然比的發(fā)音特征方法。該方法將多個基于深度神經(jīng)網(wǎng)絡的發(fā)音特征提取器用于生成幀級別的對數(shù)似然比,然后將對數(shù)似然比組成的發(fā)音特征用于PET的檢測,為學習者提供發(fā)音位置和發(fā)音方法的正音信息。實驗結果表明,發(fā)音特征對PET的檢測效果優(yōu)于常用聲學特征(MFCC,PLP和f Bank),當發(fā)音特征與MFCC特征相結合時,可以進一步提升性能,達到錯誤接受率為5.0%,錯誤拒絕率為30.8%,診斷正確率為89.8%的檢測效果。
[Abstract]:In order to improve the detection effect of pronunciation bias trend in CAPTT system, and ensure the accuracy and effectiveness of feedback information, A method of pronunciation feature based on logarithmic likelihood ratio (LLR) is proposed, in which several speech feature extractors based on depth neural network are used to generate logarithmic likelihood ratio at frame level, and then the pronunciation feature composed of logarithmic likelihood ratio is used for PET detection. The experimental results show that pronunciation features are more effective than common acoustic features, such as PET and f BankP, and can further improve the performance when the pronunciation features are combined with MFCC features. The error acceptance rate is 5.0%, the error rejection rate is 30.8%, and the diagnostic accuracy rate is 89.8%.
【作者單位】： 北京語言大學信息科學學院;
【基金】：北京語言大學梧桐創(chuàng)新平臺項目(16PT05)和北京語言大學研究生創(chuàng)新基金項目(16YCX160)資助
【分類號】：H01;TP391.7

【相似文獻】

相關會議論文 前1條

1 盧東斌;李光球;江虹;;基于比特對數(shù)似然比GSC的MQAM性能分析[A];浙江省電子學會2006年學術年會論文集[C];2006年

，

本文編號：1576528