This paper describes speaker-independent word recognition based on a new neural network model (Dynamic p r o gramming Neural Network; DNN), which can treat timesequence patterns. The proposed model, DNN, is based on the integration of multi-layer neural network and dynamic programming based matching. Speaker-independent is@ lated Japanese digit recognition experiments were carried out using data uttered by 107 speakers (50 speakers for training and 57 speakers for testing). As a result, 99.3% recognition accuracy was obtained. This suggests that the proposed model can be effective for speech recognition.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.