听觉模型倒谱系数及其在声目标识别中的应用

针对目前广泛采用的美尔倒谱系数(MFCC)鲁棒性不足的问题，基于人类听觉模型提出了一种可用于战场声目标识别的倒谱系数. 用小波包变换代替了传统的傅里叶变换，克服了傅里叶变换在频域上单分辨率的缺陷和对噪声的敏感性. 用指数压缩替换固定的对数压缩，较好地模拟了人耳处理信号的非线性能力. 在SensIT实验数据和外场实际采集的低空目标数据上的实验结果表明：相对于经典的美尔倒谱系数，本文提出的倒谱系数在识别准确性和抗噪声能力方面都有较明显的提高．

Cepstrum Coefficient Based on Human Auditory Model with Application to Recognition of Acoustic Targets

This paper proposes a cepstrum coefficient model to overcome deficiency in the classic Mel-frequency cepstral coefficients (MFCC). Based on the human auditory model, two improvements are made in computing the new cepstrum features for acoustic target recognition. First, by allowing variable time-frequency resolution and to be immune to noise, wavelet packet transform (WPT) is used instead of FFT in the computation of classic MFCC. This overcomes deficiency of single resolution and reduces sensitivity to complicated battlefield environments. Second, based on the human auditory model, compression with the exponential-law is used instead of the fixed logarithm amplitude spectrum used in the classic MFCC. Experimental results show that the new algorithm can achieve significant advancement over the former method in accuracy and robustness.