<![CDATA[ABSTRACT The capabilities of microcontrollers are currently developing rapidly. Thanks to Moore's Law, the number of embedded transistors is growing exponentially. This has led to increasingly sophisticated microcontroller capabilities that are inversely proportional to price, so that we can now embed artificial intelligence on microcontrollers with the help of one of Google's APIs, TensorFlow Lite. In this final project research, a voice command detection and recognition system will be designed using a 32-bit microcontroller in the form of an ESP32 module with WiFi connectivity as the main processor to perform data processing and recognition in the form of voice commands. Voice input is taken using a MEMS (Micro Electro Mechanical System) microphone using the I2C interface. The data sent has a width of 8 bits with a sampling frequency of 44 kHz. The sampling data results will be used in the artificial intelligence training and testing process, together with a voice command library collection with a data size of 4 GB consisting of 20 word files in English, Indonesian, and noise or environmental background samples. Training and testing are carried out by converting the results of the voice signal sampling data into voice spectrum images for input to the CNN (Convolutional Neural Network) algorithm. The results of the experiment show that the voice command recognition process has an accuracy of 90% with a recognition time of less than 1 second. Keyword : esp32,Voice, CNN, MEMS, tensorflow Lite]]>
Copyrights © 2023
