Speaker Counting by Scattered Microphone Array Based on DOA and Eigenvalue Estimations in Adverse Environments

In this paper, a smart subband system for speaker counting is proposed by scattered microphone array (SMA) and using direction of arrival (DOA) estimation with adaptive eigenvalue decomposition (AED). Firstly, the recorded signals by central array are divided into subbands by using gammatone filter bank. Then, the adaptive generalized cross-correlation (GCC) algorithm is implemented on the microphone signals for different subbands. The extracted peaks’ positions are weighted, and this process is repeated on different time frames for spatial sectors in acoustical room. To complete the process, two lateral microphone arrays are considered for verification of the estimated DOAs by using of AED algorithm. The peaks’ positions in the same locations for at least 2 of 3 arrays are considered as the number of overlapped speeches. The proposed speaker counting algorithm by scattered microphone array (SCA-SMA) is compared with other works in adverse environments, which shows the superiority of the presented algorithm in adverse environments.