Workshop on the Auditory Basis of Speech Perception Keele University, UK July 15-19, 1996

A new Type of Synchrony Detector

Cristina Dobrin

Nokia Research Center, Tampere, Finland

In this paper, a real environment application of an auditory-based front end for speech recognition will be described. The auditory model used as a basis for improvement is the Seneff model, for which several small-scale applications in speech segmentation, speech analysis have been described (see refs. [1], [3]). A qualitative and quantitative comparison with the traditional FFT-based front-end is presented. Practical constraints will lead to a more suitable implementation of the feature extraction block of the auditory front-end.

Full Paper

Bibliographic reference.  Dobrin, Cristina (1996): "A new type of synchrony detector", In ABSP-1996, 301-304.