Method and system for speech enhancement in a noisy environment

摘要

There is described a method and system for enhancing speech in a noisy environment. The method operates on a frame-to-frame basis and preferably uses a Discrete Cosine Transform (DCT) to transform time-domain components of an input signal into frequency-domain components. The speech enhancement method is essentially based on a subspace approach in the so-called Bark-domain and an optimal subspace selection using a Minimum Description Length (MDL) criterion. The MDL-based subspace selection leads to a partition of the multi - dimensional space of noisy data into a noise subspace, a signal subspace and a signal-plus-noise subspace. The enhanced signal is reconstructed by applying the inverse transform to the components of the signal subspace and weighted components of the signal-plus-noise subspace, the noise subspace being nulled during this reconstruction. The resulting enhancement method provides maximum noise reduction while minimizing signal distortions such as the so-called musical residual noise encountered with conventional subtractive-type enhancement methods.