Real-valued delayless subband affine projection algorithm for acoustic echo cancellation

Acoustic echo cancellation (AEC) often involves adaptive filters with large numbers of taps, which results in poor performance in real-time applications. The utilization of delayless subband adaptive filter (DSAF) helps reduce computations and improve the overall performance. However, conventional oversampled subband adaptive filters mainly use DFT or GDFT based analysts/synthesis filter banks and generate "complex-valued" subband signals. This is particularly inefficient when applying the affine projection algorithm (APA), a popular adaptive algorithm for AEC problem, to each subband. For APA implementation, real-valued signals show higher efficiency than complex signals. In this paper, we present a real-valued delayless subband APA and study both its computational complexity and performance on AEC problems. Compared to the complex valued approach, our method achieves a better performance with lower computational cost.