5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Modelling the Recognition of Spectrally Reduced Speech

Jon Barker, Martin Cooke

Department of Computer Science, University of Sheffield, Sheffield, UK

Progress in robust automatic speech recognition may benefit from a fuller account of the mechanisms and representations used by listeners in processing distorted speech. This paper reports on a number of studies which consider how recognisers trained on clean speech can be adapted to cope with a particular form of spectral distortion, namely reduction of clean speech to sine-wave replicas. Using the Resource Management corpus, the first set of recognition experiments confirm the high information content of sine-wave replicas by demonstrating that such tokens can be recognised at levels approaching those for natural speech if matched conditions apply during training. Further recognition tests show that sine-wave speech can be recognised using natural speech models if a spectral peak representation is employed in concert with occluded speech recognition techniques.

Full Paper

Bibliographic reference.  Barker, Jon / Cooke, Martin (1997): "Modelling the recognition of spectrally reduced speech", In EUROSPEECH-1997, 2127-2130.