Research Article
Mel Frequency Cepstral Coefficient: A Review
@INPROCEEDINGS{10.4108/eai.27-2-2020.2303173, author={Shalbbya Ali and Safdar Tanweer and Syed Sibtain Khalid and Naseem Rao}, title={Mel Frequency Cepstral Coefficient: A Review}, proceedings={Proceedings of the 2nd International Conference on ICT for Digital, Smart, and Sustainable Development, ICIDSSD 2020, 27-28 February 2020, Jamia Hamdard, New Delhi, India}, publisher={EAI}, proceedings_a={ICIDSSD}, year={2021}, month={3}, keywords={speech recognition system mfcc mel frequency feature extraction}, doi={10.4108/eai.27-2-2020.2303173} }- Shalbbya Ali
Safdar Tanweer
Syed Sibtain Khalid
Naseem Rao
Year: 2021
Mel Frequency Cepstral Coefficient: A Review
ICIDSSD
EAI
DOI: 10.4108/eai.27-2-2020.2303173
Abstract
Speech is the easiest and widely used mode of communication between human beings. The development of a human computer interface for establishing a similar dialogue between the machine and humans was the inspiration behind speech recognition systems. This involves training a system so that voice recognition can be carried out. The machine has to be trained using any of the speech recognition algorithms which would extract the features of the voice and perform speech recognition. One such algorithm is the Mel-frequency Cepstral coefficient. The paper describes all the stages of the MFCC technique along with brief description of each process. It also gives a comparison between linear predictive coding and MFCC technique.
Copyright © 2020–2024 EAI