Speech Recognition With Deep Learning

Abstract

Presently, computers have already replaced a tremendous number of humans in many creative professions. Therefore, Artificial Intelligence areas are composed of Machine Learning, Natural Language Processing, Computer Vision, and Robotics. Similarly, speech recognition can be predicted by using computers. In audio files or video files that are large and have many minutes in length, many files have a variety of audio and audio files. This research chose to listen to the desired sound from a large file. In this research, deep learning was used to classify speech.The utilization of speech recognition based on deep learning has increased dramatically in the past years by using different deep learning techniques and algorithms, the main deep learning algorithms used for speech recognition are Recurrent Neural Networks (RNNs) which have introduced to take temporal dependencies into account, and  Long Short-Term Memory (LSTM)  which are a special case of RNNs, that takes long-term dependencies in a speech in addition to short term dependencies into account and the Convolutional Neural Networks (CNNs) which are effective models for reducing spectral variations and modelling spectral correlations in acoustic features for automatic speech recognition (ASR).