8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Exploiting Phoneme Similarities in Hybrid HMM-ANN Keyword Spotting

Joel Pinto, Andrew Lovitt, Hynek Hermansky

IDIAP Research Institute, Switzerland

We propose a technique for generating alternative models for keywords in a hybrid hidden Markov model - artificial neural network (HMM-ANN) keyword spotting paradigm. Given a base pronunciation for a keyword from the lookup dictionary, our algorithm generates a new model for a keyword which takes into account the systematic errors made by the neural network and avoiding those models that can be confused with other words in the language. The new keyword model improves the keyword detection rate while minimally increasing the number of false alarms.

Full Paper

Bibliographic reference.  Pinto, Joel / Lovitt, Andrew / Hermansky, Hynek (2007): "Exploiting phoneme similarities in hybrid HMM-ANN keyword spotting", In INTERSPEECH-2007, 1817-1820.