Academic Journals Database
Disseminating quality controlled scientific knowledge

Speech Recognition Using HMM with MFCC-An Analysis Using Frequency Specral Decomposion Technique

Author(s): Ibrahim Patel | Y. Srinivas Rao

Journal: Signal & Image Processing
ISSN 2229-3922

Volume: 1;
Issue: 2;
Start page: 101;
Date: 2011;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Speech-recognition | Mel-frequencies | DCT | frequency decomposition | Mapping Approach | HMM | MFCC.

This paper presents an approach to the recognition of speech signal using frequency spectral informationwith Mel frequency for the improvement of speech feature representation in a HMM based recognitionapproach. A frequency spectral information is incorporated to the conventional Mel spectrum base speechrecognition approach. The Mel frequency approach exploits the frequency observation for speech signal ina given resolution which results in resolution feature overlapping resulting in recognition limit. Resolutiondecomposition with separating frequency is mapping approach for a HMM based speech recognitionsystem. The Simulation results show an improvement in the quality metrics of speech recognition withrespect to computational time, learning accuracy for a speech recognition system.
Why do you need a reservation system?      Save time & money - Smart Internet Solutions