期刊名称：Signal & Image Processing : An International Journal (SIPIJ)
印刷版ISSN：2229-3922
电子版ISSN：0976-710X
出版年度：2010
卷号：1
期号：2
页码：101
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：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.
关键词：Speech-recognition; Mel-frequencies; DCT; frequency decomposition; Mapping Approach; HMM; MFCC
Loading...
