Abstract
Digital processing of speech signal and the voice recognition algorithm is very important for fast and accurate automatic scoring of the recognition technology. A voice is a signal of infinite information. The direct analysis and synthesis of a complex speech signal is due to the fact that the information is contained in the signal.
 Speech is the most natural way of communicating people. The task of speech recognition is to convert speech into a sequence of words using a computer program.
 This article presents an algorithm of extracting MFCC for speech recognition. The MFCC algorithm reduces the processing power by 53% compared to the conventional algorithm. Automatic speech recognition using Matlab.
Highlights
Automatic speech recognition is a dynamically developing area in the field of artificial intelligence
It was noted that the MFCC for each individual user is unique
Certain variations were observed due to differences in the locality of the recording area. These MFCC are compared, that is, the MFCC pattern and the real-time input are compared for each user
Summary
Automatic speech recognition is a dynamically developing area in the field of artificial intelligence. The amplitude of the sound signal is influenced by a number of factors: the volume of the speaker's voice, its distance from the microphone, etc. As can be seen from the study, the use of normalization always allows to reduce the volume spread for different utterances These results were obtained for a speech database collected under the same conditions on the only available equipment, so in general, normalization played a minor role.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
