Hybrid learning scheme for modular-based phoneme recognizer

Abbas Ahmadi, Fakhri Karray, Mohamed Kamel

Abstract: This paper proposes a hybrid learning scheme for modular-based recognizer for a problem of phoneme recognition. The scheme is established by combining two types of classifiers which are statistical and neural network-based ones. First, an initial modular topology is built employing statistical-based classifier and then, neural network-based classifiers are used as discriminators or local experts of the modular-based recognizer. To apply modular systems, we propose a new concept called phoneme family. We utilize k-means clustering method to obtain the families. An unknown phoneme is first fed into a corresponding module through classifier selector. Next, the exact label of the phoneme is determined within the module. Encouraging results are obtained by applying the proposed method on TIMIT database.