Speech Enhancement using Kernel and Normalized Kernel Affine Projection Algorithm
This work addresses noise removal for applications like speech recognition and hearing aids, but it is incremental as it builds on existing kernel adaptive filter methods.
The paper tackled speech enhancement by applying Kernel Affine Projection Algorithm (KAPA) and Normalized KAPA in Reproducing Kernel Hilbert Space (RKHS) to remove background noise, achieving improved signal-to-noise ratio values compared to conventional adaptive filters in experiments using the NOIZEUS database.
The goal of this paper is to investigate the speech signal enhancement using Kernel Affine Projection Algorithm (KAPA) and Normalized KAPA. The removal of background noise is very important in many applications like speech recognition, telephone conversations, hearing aids, forensic, etc. Kernel adaptive filters shown good performance for removal of noise. If the evaluation of background noise is more slowly than the speech, i.e., noise signal is more stationary than the speech, we can easily estimate the noise during the pauses in speech. Otherwise it is more difficult to estimate the noise which results in degradation of speech. In order to improve the quality and intelligibility of speech, unlike time and frequency domains, we can process the signal in new domain like Reproducing Kernel Hilbert Space (RKHS) for high dimensional to yield more powerful nonlinear extensions. For experiments, we have used the database of noisy speech corpus (NOIZEUS). From the results, we observed the removal noise in RKHS has great performance in signal to noise ratio values in comparison with conventional adaptive filters.