All Title Author
Keywords Abstract

Research on Speech Recognition Based on Neural Networks

Keywords: neural networks , speech recognition , recurrent neural network , multi layer perceptron , linear prediction , vector quantization

Full-Text   Cite this paper   Add to My Lib


Because of good characteristics of the abstract classification, neural networks have become an effective tool for resolving issues related to recognition, and have been applied to the research and development of speech recognition system. A speech recognizer system comprises of two blocks, Feature Extractor and Recognizer. For increasing the recognition accuracy, this paper proposes two types of speech recognition system whose recognition block uses the recurrent neural network(RNN) and multi layer perceptron(MLP) respectively. Furthermore, the main work steps of Feature Extractor (FE) block is introduced and the structure of two types of neural networks mentioned above is discussed. Using a standard LPC Cepstrum, the FE translates the input speech into a trajectory in the LPC Cepstrum feature space. The recognizer block discovers the relationships between the trajectories and recognizes the word. The results show that the MLP's recognition accuracies were better than the RNN's,while the RNN's recognition accuracies achieved 85%.


comments powered by Disqus

Contact Us


微信:OALib Journal