Separation of Overlapping Sound using Nonnegative Matrix Factorization

One of the most common problems in sound recognition is the overlapping sound. This phenomena requires sound separation beforehand in order to be recognized. Most studies related to sound separation used artificial data in their research, i.e. using experiment sound data from a controlled environment which is augmented with one or more sound types, and achieve good results. However, when it is implemented in the real condition, it’s performance has dropped dramatically. Thus, in this research we use overlapping data recorded in real environments. The purpose of this research is to separate the speech and non-speech, and noise by using the Non-negative Matrix Factorization (NMF). Our experimental results show that the NMF works well when separating sound and non-sound, and has helped the performance of sound recognition.