Nuance Communications, Inc.

Abdel-rahman Mohamed

Tara N Sainath

Bhuvana Ramabhadran

Brian E D Kingsbury

Techniques for learning front-end speech recognition parameters as part of training a neural network classifier include obtaining an input speech signal, and applying front-end speech recognition parameters to extract features from the input speech signal. The extracted features may be fed through a neural network to obtain an output classification for the input speech signal, and an error measure may be computed for the output classification through comparison of the output classification with a known target classification. Back propagation may be applied to adjust one or more of the front-end parameters as one or more layers of the neural network, based on the error measure.

Growing community of inventors

Toronto, Canada

Abdel-rahman Mohamed