Abstract: Speech enhancement is a long standing problem with
numerous applications like teleconferencing, VoIP, hearing aids and
speech recognition. The motivation behind this research work is to
obtain a clean speech signal of higher quality by applying the optimal
noise cancellation technique. Real-time adaptive filtering algorithms
seem to be the best candidate among all categories of the speech
enhancement methods. In this paper, we propose a speech
enhancement method based on Recursive Least Squares (RLS)
adaptive filter of speech signals. Experiments were performed on
noisy data which was prepared by adding AWGN, Babble and Pink
noise to clean speech samples at -5dB, 0dB, 5dB and 10dB SNR
levels. We then compare the noise cancellation performance of
proposed RLS algorithm with existing NLMS algorithm in terms of
Mean Squared Error (MSE), Signal to Noise ratio (SNR) and SNR
Loss. Based on the performance evaluation, the proposed RLS
algorithm was found to be a better optimal noise cancellation
technique for speech signals.
Abstract: Various sounds generated in the chest are included in
auscultation sound. Adaptive Noise Canceller (ANC) is one of the
useful techniques for biomedical signal. But the ANC is not suitable
for auscultation sound. Because the ANC needs two input channels as
a primary signal and a reference signals, but a stethoscope can
provide just one input sound. Therefore, in this paper, it was
proposed the Single Input ANC (SIANC) for suppression of breath
sound in a cardiac auscultation sound. For the SIANC, it was
proposed that the reference generation system which included Heart
Sound Detector, Control and Reference Generator. By experiment
and comparison, it was confirmed that the proposed SIANC was
efficient for heart sound enhancement and it was independent of
variations of a heartbeat.