First European Conference on Speech Communication and Technology

Paris, France
September 27-29, 1989

An Adaptive Voiced/Unvoiced Speech Classifier

T. J. Moulsley, P. R. Holmes

Philips Research Laboratories, Redhill, Surrey, UK

This paper discusses pattern recognition techniques for classification of speech into voiced and unvoiced sounds. An algorithm is described which is capable of adapting to changing speaker characteristics, spectral distortion and background noise. Robust speech parameters are used in a computationally efficient multi-dimensional classifier which requires no training data base.

Full Paper

Bibliographic reference.  Moulsley, T. J. / Holmes, P. R. (1989): "An adaptive voiced/unvoiced speech classifier", In EUROSPEECH-1989, 1466-1469.