how can i use DWT for extracting the features of isolated words
Posts: 14,118
Threads: 61
Joined: Oct 2014
Voice-to-computer interface is the next big step that technology needs for general users. Automatic Speech Recognition (ASR) will play an important role in bringing technology to people. There are numerous voice recognition applications such as direct voice input on aircraft, data entry, voice-to-text processing, voice user interfaces such as voice dialing. The ASR system can be divided into two different parts: feature extraction and feature recognition. This paper presents the extraction of features based on MATLAB using Mel Frequency Cepstrum Coefficients (MFCC) for ASR. The MFCC algorithm makes use of the Mel frequency filter bank along with several other signal processing operations. The MFCC features matrix obtained from our implementation of the MFCC algorithm has a number of rows equal to the number of input frames and is used in the feature recognition phase.
It can be understood in the following video: