A study on noise reduction system based on ALE and noise reconstruction filter

A noise reduction technique to cancel wideband and sinusoidal noise in noisy speech is proposed. In actual environments, the background noise frequently includes sinusoidal noise, for example ventilating fan noise. Therefore, it is important to reduce sinusoidal noise. We have proposed a noise reconstruction system (NRS) with adaptive line enhancer (ALE). However, the quality of the enhanced speech is remarkably degraded. In order to solve the problem, we propose a new noise reduction system which uses two types of ALE and a noise reconstruction filter (NRF). First, the two ALEs estimate the speech components. However, since two ALEs cannot estimate the unvoiced sound, the quality of the speech enhanced by the two ALEs is inadequate. Thus, the NRF is used to improve the noise reduction ability. The NRF accurately estimates the background noise from the signal occupied by the noise components, which is obtained by subtracting the speech enhanced by the two ALEs from the noisy speech. The enhanced speech is obtained by subtracting the reconstructed noise from the noisy speech. Finally, the cascaded structure of the noise reduction system is proposed to improve further the quality of the enhanced speech.