Title :
Modified two-dimensional root cepstrum analysis
Author :
Marvi, H. ; Chilton, E.
Author_Institution :
Dept. of Electr. Eng., Shahrood Univ. of Technol., Iran
fDate :
3/3/2005 12:00:00 AM
Abstract :
A novel feature vector for speech recognition applications is proposed. These new features are obtained by generalising the two-dimensional root cepstrum (TDRC) using the Mel-scaled root filter bank energies of a speech frame in the process of computing the TDRC. Results indicate superior performance over conventional techniques in an isolated word recognition problem.
Keywords :
cepstral analysis; channel bank filters; speech recognition; Mel-frequency cepstral coefficients; Mel-scaled root filter bank; feature vector; isolated word recognition; modified 2D root cepstrum analysis; modified two-dimensional root cepstrum analysis; speech frame; speech recognition applications;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20047943
