BMAC DLA- A Novel Approach to SpeechH Recognition

Abstract — Accessing a device through Speech recognition is a new research area. It provides users an easier way to search for information using voice. Recent advances in mobile technology have enabled users of voice recognition products to achieve desirable results. One of the most important reasons that led to the production a large number of voice input systems is the ability of the voice input systems to remove a lot of literacy barriers in communicating with the devices. Current work proposes multilayer Perceptron neural network based speech recognition method, the framework for controlling systems through Voice recognition approach. It uses several commands for recognition of the voices and trains the engine to the voice of different users. It can provide a foundation for improving the communication, learning and teaching environments. However, not all potential users have the capabilities that allow them to use the existing methodologies. This model provides the opportunity to operate the mobile or desktop devices without using the keypad. Experimental result provides better result when compare with the conventional methods