Speech recognition with deep learning neural networks

The speech recognition or automatic speech recognition is a branch of applied computer science, the engineering and computational linguistics. It is concerned with the investigation and development of processes that make automatic, especially computers, the spoken language available for automatic data acquisition. The speech recognition is to be distinguished from the voice or speaker identification, a biometric method of personal identification. However, the realizations of these procedures are similar. In this thesis the deep learning method is used to recognize words from human speech signals. For implementation of proposed method Python is used and presented in a step-by-step manner. The CNN turned out to be a really good tool in speech recognition and encourage to build more complex architecture in case of more labels. The TensorFlow Speech Recognition Challenge Kaggle is used to check out more solutions. KEYWORDS:Speech recognition, artificial neural network, deep learning