A review of supervised learning algorithms for single channel speech enhancement

Abstract

Reducing interfering noise in a noisy speech recording has been a difficult task in many applications related to the voice. From hands-free communication to human–machine interaction, a speech signal of the interest captured by a microphone is always mixed with the interfering noise. The interfering noise appends new frequency components and masks a large portion of the time-varying spectra of the desired speech. This significantly affects our perception of the desired speech when listening to the noisy observations. Therefore, it is extremely desirable and sometimes even crucial to clean the noisy speech signals. This clean-up process is referred to as the speech enhancement (SE). SE aims to improve the speech intelligibility and quality of the voice for the communication. We present a comprehensive review on the supervised single channel speech enhancement (SCSE) algorithms. First, a classification based overview of the supervised SCSE algorithms is provided and the related works is outlined. The recent literature on the SCSE algorithms in supervised perspective is reviewed. Finally, some open research problems are identified that need further research.