DocumentCode :
2898199
Title :
Speaker-independent vowel recognition: spectrograms versus cochleagrams
Author :
Muthusamy, Yeshwant K. ; Cole, Ronald A. ; Slaney, Malcolm
Author_Institution :
Dept. of Comput. Sci. & Eng., Oregon Graduate Inst. of Sci. & Technol., Beaverton, OR, USA
fYear :
1990
fDate :
3-6 Apr 1990
Firstpage :
533
Lastpage :
536
Abstract :
The ability of multilayer perceptrons (MLPs) trained with backpropagation to classify vowels excised from natural continuous speech is examined. Two spectral representations are compared: spectrograms and cochleagrams. The features used to train the MLPs include discrete Fourier transform (DFT) or cochleagram coefficients from a single frame in the middle of the vowel, or coefficients from each third of the vowel. The effects of estimates of pitch, duration, and the relative amplitude of the vowel were investigated. The experiments show that with coefficients alone, the cochleagram is superior to the spectrogram in classification performance for all experimental conditions. With the three additional features, however, the results are comparable. Perceptual experiments with trained human listeners on the same data revealed that MLPs perform much better than humans on vowels excised from context
Keywords :
Fourier transforms; learning systems; neural nets; spectral analysis; speech recognition; backpropagation; cochleagrams; discrete Fourier transform; multilayer perceptrons; pitch; speaker independent vowel recognition; spectrograms; speech recognition; Amplitude estimation; Backpropagation; Biomembranes; Computer science; Discrete Fourier transforms; Ear; Filters; Frequency; Hair; Humans; Multilayer perceptrons; Spectrogram; Speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on
Conference_Location :
Albuquerque, NM
ISSN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.1990.115767
Filename :
115767
Link To Document :
بازگشت