一种结合听觉掩蔽与双耳互相关的声源定位算法

A SOUND SOURCE LOCALISATION ALGORITHM BASED ON THE COMBINATION OF AUDITORY MASKING AND BINAURAL CROSS-CORRELATION

针对基于双耳互相关(BCC)的声源定位算法在噪声里定位精度下降的问题,提出一种结合听觉掩蔽谱减法与双耳互相关的声源定位算法。该算法在双耳互相关时延估计之前采用一种基于听觉掩蔽的谱减法算法,有效压缩左耳和右耳信号中的噪声,提高信噪比。通过与双耳互相关声源定位算法的结合,提高了双耳时间差估计的准确性,从而提高了整个声源定位的精度。实验结果表明,该算法能够有效减少噪声带来的定位误差,提高声源定位精度。

In the noisy environment,the localisation accuracy of sound source localisation algorithm based on binaural cross-correlation（ BCC） will deteriorate. In order to solve this problem,in this paper we propose a sound source localisation algorithm which combines the auditory masking-based spectral subtraction algorithm with the binaural cross-correlation. Before estimating the time-delay of binaural cross-correlation,the algorithm uses an auditory masking-based spectral subtraction algorithm,and effectively compresses the noises in signals of both left and right ears and raises the signal-to-noise ratio as well. Through combining with the binaural cross-correlation sound source localisation algorithm,this algorithm improves the accuracy of the interaural time difference estimation,and therefore meliorates the whole accuracy of sound source localisation. Experimental result shows that this algorithm is able to effectively reduce the localisation error caused by the noises,and to improve the accuracy of sound resource localisation.