Accurate keyword spotting using strictly lexical fillers

Our goal is to design an accurate keyword spotter that can deal with any size of keyword set, since the size actually required in a wide range of applications is large (number of airports, number of names in a directory, etc.). This justi es the choice of an architecture based on a large-vocabulary continuous-speech recognizer. In a previous paper [1] we introduced the use of strictly-lexical subword llers for keyword spotting based on the INRS large-vocabulary continuous-speech recognizer [2] showing that they are, when compared to acoustic llers, a good compromise between memory and time consumption, keyword choice freedom and task-independence training on one hand and accuracy on the other hand. We propose here two new high-performance designs of individual strictly-lexical subword llers that perform, this time, better than their acoustic counterparts while still keeping the mentioned advantages.