About This Course
Join "Automatic Speech Recognition with DeepSpeech, Python and ROS Integration" on Robociti to advance your Speech Processing skills and explore how to build an Automatic Speech Recognition (ASR) module that can process a live or pre-recorded audio stream in order to recognize words and sentences of the English language according to a pre-trained vocabulary and produce the transcript of the given speech snippet. To achieve this, the popular ASR model DeepSpeech is used, along with Python programming and ROS (Robot Operating System) for further integration in larger projects in AI and Robotics that require this End-To-End module. Firstly, students are taught the basics about the structure of the DeepSpeech ASR model using RNNs. Then, the core parameters needed to use DeepSpeech are presented in order to create accurate Speech Recognition predictions. Finally, the module is integrated into the ROS framework for easier use with other modules in robotic and AI applications.
Course Features
- check_circle Programming Environment
- check_circle Jupyter Notebook
- check_circle Forum & Support
Course Chapters
DeepSpeech Structure
Robot Management
WorkSpace Setup
DeepSpeech introduction
Inferences with DeepSpeech
Voice activity detection
Ros integration
Course Completion