Summary: Modeling Consistency in a Speaker Independent
Continuous Speech Recognition System
Yochai Konig, Nelson Morgan, Chuck Wooters
International Computer Science Institute
1947 Center Street, Suite 600
Berkeley, CA 94704, USA.
Victor Abrash, Michael Cohen, Horacio Franco
SRI International
333 Ravenswood Ave.
Menlo Park, CA 94025, USA
Abstract
We would like to incorporate speaker­dependent consistencies, such as
gender, in an otherwise speaker­independent speech recognition system.
In this paper we discuss a Gender Dependent Neural Network (GDNN)
which can be tuned for each gender, while sharing most of the speaker
independent parameters. We use a classification network to help generate
gender­dependent phonetic probabilities for a statistical (HMM) recogni­
tion system. The gender classification net predicts the gender with high
accuracy, 98.3% on a Resource Management test set. However, the in­
tegration of the GDNN into our hybrid HMM­neural network recognizer

Source: Abrash, Victor - Speech Technology & Research Laboratory, SRI International

Collections: Computer Technologies and Information Sciences