Second European Conference on Speech Communication and Technology

Genova, Italy
September 24-26, 1991


Phoneme Recognition with an Artificial Neural Network

K. Elenius, G. Takacs

Department of Speech Communication and Music Acoustics, KTH, Stockholm, Sweden

An artificial neural network has been trained to recognize phonemes using the error back-propagation technique. First a coarse feature network is trained to extract seven quasi-phonetic features from the spectral frames of a Bark-scaled filter bank. The outputs of this net and the spectral outputs of the filter bank were input to a phoneme recognition net. The coarse features were recognized with 80% - 93% accuracy. Using manual segmentation the phone recognition rate was 64% and in 82% of the cases, the correct phone was among the best three candidates. Keywords: speech recognition; phoneme recognition; backword propagation; artificial neural networks

Full Paper

Bibliographic reference.  Elenius, K. / Takacs, G. (1991): "Phoneme recognition with an artificial neural network", In EUROSPEECH-1991, 121-124.