摘要
为了提高低信噪比下语种识别的准确率,引入一种新的特征提取融合方法.在前端加入有声段检测,并基于人耳听觉感知模型提取伽玛通频率倒谱系数(Gammatone Frequency Cepstrum Coefficient,GFCC)特征,通过主成分分析对特征进行压缩、降噪,融合每个有声段的Teager能量算子倒谱参数,通过高斯混合通用背景模型进行语种识别验证.实验结果表明,在信噪比为-5~0 dB时,相对于基于对数梅尔尺度滤波器组能量特征方法,融合特征集方法对5种语言的识别率,分别提升了23.7%~34.0%,其他信噪比等级下识别率也有明显的提升.
In order to improve the accuracy of language recognition at low signal-to-noise ratios,a new feature extraction fusion method is introduced,which incorporates voiced segment detection at the front end of feature extraction.Based on the human ear auditory perception model,the Gammatone Frequency Cepstrum Coefficients(GFCC)are extracted as feature parameters,which are compressed and de-noised by principal component analysis and are fused with the Teager energy operator cepstrum parameters for each audible segment.Experiments with the Gaussian mixture general background model for language recognition show that the method based on the fused feature set improves the recognition accuracy of the five languages by 23.7%to 34.0%at signal-to-noise ratios ranging from-5 dB to 0 dB respectively,compared to the method based on the energy features of the log-Mel scale filter bank,and also significantly improves the recognition accuracy at other signal-to-noise levels.
作者
刘晶
邵玉斌
龙华
李一民
LIU Jing;SHAO Yu-bin;LONG Hua;LI Yi-min(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,Yunnan,China)
出处
《云南大学学报(自然科学版)》
CAS
CSCD
北大核心
2022年第2期254-261,共8页
Journal of Yunnan University(Natural Sciences Edition)
基金
国家自然科学基金(61761025)。
关键词
语种识别
伽玛通频率倒谱系数
有声无声段检测
Teager能量算子倒谱参数
主成分分析
language identification
Gammatone Frequency Cepstrum Coefficients(GFCC)
sound and unvoiced segment detection
Teager energy operator cepstrum parameter
principal component analysis