An Enhanced Voice Assistance using Recurrent Neural Network

The preceding decade has brought huge development in voice assistants. The speech recognition system along with cognitive and linguistic system are interdisciplinary areas that contribute to the field of speech construction and auditory observation. This study aims at developing a speech recognition system with the help of Recurrence Neural Network (RNN), a deep learning model for identifying the voice signals. This mechanism reduces the use of input devices and hardly requires more knowledge on feature selection. The hidden layers monitor the time sequence of audio signals between the transformation from one layer to another. The word error rate is the metric used to evaluate the efficiency of the model based on the number pf epochs and the input size.