The Continuous Wavelet Transform (CWT) processed through a U-Net significantly improved phonocardiogram denoising performance by 2 to 8 dB over the standard Short-Time Fourier Transform.
Continuous wavelet transform combined with a U-Net architecture significantly improves the denoising of heart sound signals compared to standard short-time Fourier transform methods.
Effect estimate: 2 to 8 dB improvement
Abstract Cardiovascular diseases are the leading cause of death worldwide. Automatic heart sound analysis offers a low-cost and highly promising diagnostic method, but its effectiveness is often compromised by noise during recording. Nowadays, most advanced blind source separation methods typically employ deep learning techniques based on a U-Net architecture with a short-time Fourier transform (STFT) for time-frequency representation of audio signals. However, alternative time-frequency representations have not been thoroughly explored. In this paper, we enhance phonocardiogram signal denoising by utilizing four distinct time-frequency representations: STFT, continuous wavelet transform (CWT), wavelet synchrosqueezed transform, and the S-transform, processed through a U-Net. We evaluated our denoising algorithm by contaminating heart sound signals with four different types of noise, including non-stationary real-world nuisance signals, at -5 dB and 0 dB signal-to-noise ratios (SNRs). Our results showed that the CWT achieved the best denoising performance, with gains of over 18 dB for heart sounds contaminated with speech at -5 dB SNR. We found that the CWT significantly improves by 2 to 8 dB over STFT while requiring less than double the computational resources. The method’s effectiveness is demonstrated in the time domain, time-frequency, and power spectral density spaces, resulting in a denoising model that surpasses current state-of-the-art techniques.
González–rodríguez et al. (Mon,) conducted a other in Heart sound analysis (Phonocardiogram denoising) (n=1,000). Continuous Wavelet Transform (CWT) processed through a U-Net vs. Short-Time Fourier Transform (STFT) processed through a U-Net was evaluated on Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) (2 to 8 dB improvement). The Continuous Wavelet Transform (CWT) processed through a U-Net significantly improved phonocardiogram denoising performance by 2 to 8 dB over the standard Short-Time Fourier Transform.