Extracting MFCC features from audio samples
When building an ML application with Edge Impulse, the impulse is responsible for all of the data processing, such as feature extraction and model inference.
In this recipe, we will see how to design an impulse to extract MFCC features from the audio samples.
Getting ready
Let's start this recipe by discussing what an impulse is and examining the MFCC features used for our KWS application.
In Edge Impulse, an impulse is responsible for data processing and consists of two computational blocks, mainly the following:
- Processing block: This is the preliminary step in any ML application, and it aims to prepare the data for the ML algorithm.
- Learning block: This is the block that implements the ML solution, which aims to learn patterns from the data provided by the processing block.
The processing block determines the ML effectiveness since the raw input data is often not suitable for feeding the model directly...
