ABSTRACT
This chapter introduces the basic spectral subtraction algorithm and describes some of the variations of the algorithm aimed at reducing speech and noise distortion. The spectral-subtractive algorithm is historically one of the first algorithms proposed for noise reduction. More papers have been written describing variations of this algorithm than any other algorithm. It is based on a simple principle. Assuming additive noise, one can obtain an estimate of the clean signal spectrum by subtracting an estimate of the noise spectrum from the noisy speech spectrum. The simple subtraction processing comes at a price. The subtraction process needs to be done carefully to avoid any speech distortion. If too much is subtracted, then some speech information might be removed, whereas if too little is subtracted, then much of the interfering noise remains.
