Applying Hybrid Neural Network For Malay Syllables Speech Recognition

We proposed a hybrid technique for speech recognition which applying 2 different neural network architecture. The proposed technique combines self-organizing map (SOM) which known as unsupervised network and multilayer perceptron (MLP) which known as supervised network for Malay syllables speech recognition. We used a 2D self-organizing feature map as a feature extractor which acts as a sequential mapping function in order to transform the acoustic vector sequences of speech signal into trajectories. The output of SOM is a matrix with same dimension and its elements take on binary values. The transformation of the feature vector simplifies the classification task by recognizer using multilayer perceptron. The MLP classifies the binary trajectories that each syllable corresponds to. Experiments were conducted on the 15 Malay syllables by 10 speakers for conventional technique (MLP only) and proposed technique (SOM and MLP). Our technique has achieved better performance where improves the accuracy up to 4.5%.