Acoustic features for speech recognition

The extraction and selection of acoustic features is an important part of speech recognition. The extraction of acoustic features is both a process of substantial compression of information and a signal deconvolution process, in order to enable the pattern divider to better divide. Due to the time-varying nature of speech signals, feature extraction must be performed on a small segment of the speech signal, i.e., a short-time analysis is performed. This interval of analysis, which is considered smooth, is called a frame, and the offset between frames is usually taken as 1/2 or 1/3 of the frame length. the signal is usually pre-emphasized to boost high frequencies, and a window is added to the signal to avoid the effects of the edges of the short-duration speech segment.