Book Image

Python Deep Learning Cookbook

By : Indra den Bakker
Book Image

Python Deep Learning Cookbook

By: Indra den Bakker

Overview of this book

Deep Learning is revolutionizing a wide range of industries. For many applications, deep learning has proven to outperform humans by making faster and more accurate predictions. This book provides a top-down and bottom-up approach to demonstrate deep learning solutions to real-world problems in different areas. These applications include Computer Vision, Natural Language Processing, Time Series, and Robotics. The Python Deep Learning Cookbook presents technical solutions to the issues presented, along with a detailed explanation of the solutions. Furthermore, a discussion on corresponding pros and cons of implementing the proposed solution using one of the popular frameworks like TensorFlow, PyTorch, Keras and CNTK is provided. The book includes recipes that are related to the basic concepts of neural networks. All techniques s, as well as classical networks topologies. The main purpose of this book is to provide Python programmers a detailed list of recipes to apply deep learning to common and not-so-common scenarios.
Table of Contents (21 chapters)
Title Page
About the Author
About the Reviewer
Customer Feedback

Implementing a speech recognition pipeline from scratch

Speech recognition, also known as Automatic Speech Recognition (ASR) and speech-to-text (STT/S2T),  has a long history. More traditional AI approaches have used in the for a long time; however, with recent interest in deep learning speech, recognition is getting a new boost in performance. Many major tech companies of the world have an interest in speech recognition of the different for it can be used, for example, Voice Search by Google, Siri by Apple, and Alexa by Amazon.

Many companies use pre-trained recognition software. However, in the following recipe, we will demonstrate how to implement and train a speech recognition pipeline from scratch. The accuracy of this newly trained model will be lower than the ones used in the industry. The main reason is that the quality and volume of the training data play a crucial role in accuracy. Interestingly enough, there is a lot of training data (thousands of hours of open source data...