摘要
主要论述加性和卷积性噪声条件下语音识别的抗噪方法.在特征提取阶段,用功率谱短时均值相减的谱减方法补偿加性噪声的影响,用在Mel频标倒谱域RASTA(relativespectral)滤波补偿卷积性噪声对语音识别系统的影响.在汉语非特定人孤立数字识别实验中,使用该方法的误识率比未使用该方法要低,并且需要很小的噪声先验知识和假设,运算简单.实验证明,提出的减谱结合RASTA的方法是一种比较有效地削减噪声的方法.
Discusses noise suppression in speech recognition under conditions of additive and convolutional noise. In the step of feature extraction the effect of additive noise is compensated by spectral subtraction based on short time mean values of the power spectrum, and convolutional noise is compensated by the RASTA (relative spectral) technology on Mel frequency cepstrum. Experiments on speakerindependent mandarin isolated digits recognition showed that word error rates with the proposed method are lower than those without it. Moreover, the method needs less apriori knowledge of the noise and has lower complexity in calculation. The proposed method based on spectral subtraction and RASTA is an effective method in noise suppression.
出处
《北京理工大学学报》
EI
CAS
CSCD
北大核心
2003年第5期621-624,共4页
Transactions of Beijing Institute of Technology
关键词
语音识别
噪声削减
谱减
RASTA
speech recognition
noise suppression
spectral subtraction
relative spectral
