About This Course
Join "Introduction to Speech Recognition with Neural Networks", the most fundamental course regarding audio processing with computers and its applications on Robociti, to get introduced to basic concepts about audio, how to process it with computers and especially about how to perform speech recognition. Firstly, this course introduces the basic properties of sound that we need to take into consideration when dealing with audio signals, along with how to perform sampling for digital processing using Python commands. Then, transformations according to frequency are explained in order to perform speech recognition with greater ease. Finally, Convolutional and Recurrent Neural Networks are proposed for improving the accuracy of our speech recognition models.
Course Features
- check_circle Programming Environment
- check_circle Jupyter Notebook
- check_circle Forum & Support
Course Chapters
Fundamental Principles
Robot Management- WorkSpace Setup
- About natural language processing
- Sound processing in computers
- Sound sample analyse
- Language processing and natural network
- Analyse a sample of your voice
- Course Completion
