In framing of audio samples' in audio feature extraction, what is need of frame shift while giving frame size?? i.e. frame size = 20ms, frame shift = 10ms. Rather then shifting/overlapping why can't we use continuous frames then of overlapped??
- By performing the windowing with overlap we are artificially increasing our time resolution (larger granularity of features in time). This is especially useful when frame duration is long (bad time resolution, very good frequency resolution), thus yielding kind of extra 'time resolution'.
- Usually no one is using the rectangular window, but other types such as Hamming, Hann, etc. As you probably know, windows tend to zero samples at both of their ends. By doing data you are kind of loosing some data. Let's imagine that you have some very short event you want to detect, at point where two windows are joined. If there is no overlap, then these samples will be almost removed. But if you perform 50% of overlap, there will be another window, right in the centre, and you won't lose anything.