This project utilizes the Arduino Nano 33 BLE Sense microcontroller to create a voice-controlled light switch. The built-in microphone captures audio signals, and a pretrained word detection model identifies the words "Yes" and "No." The LED light is switched on when "Yes" is detected and off when "No" is heard.

• Explore machine learning applications using Arduino Nano 33 BLE Sense.
• Implement voice recognition on microcontrollers.
• Test the microphone capabilities of the Arduino Nano board for real-world applications.
• Debug and modify in-built libraries and code.
• Deploy the Micro Speech application to the Arduino Nano 33 BLE Sense.

• Arduino Nano 33 BLE Sense board
• Micro USB cable for connecting the Arduino board to a desktop machine.
• Arduino IDE for programming the board.

1. Use the Arduino IDE to connect the microphone and deploy the Micro Speech application to the microcontroller.
2. Install the Arduino_TensorFlowLite-2.4.0-ALPHA-precompiled library and select the micro_speech example.
3. Modify the code in arduino_command_responder.cpp to implement the desired functions.

// ... (Previous code)

void RespondToCommand(tflite::ErrorReporter* error_reporter,
    int32_t current_time, const char* found_command,
    uint8_t score, bool is_new_command) {
    static bool is_initialized = false;
    if (!is_initialized) {
        pinMode(LED_BUILTIN, OUTPUT);
        pinMode(LEDG, OUTPUT);
        digitalWrite(LED_BUILTIN, LOW);
        digitalWrite(LEDG, HIGH);
        is_initialized = true;
    }
    static int certainty = 220;
    if (is_new_command) {
        error_reporter->Report("Heard %s (%d) @%dms", found_command, score,
            current_time);

        if (found_command[0] == 'y') {
            digitalWrite(LED_BUILTIN, HIGH);
            digitalWrite(LEDG, LOW); // turn on LED
        }

        if (found_command[0] == 'n') {
            digitalWrite(LED_BUILTIN, LOW);
            digitalWrite(LEDG, HIGH); // turn off LED
        }
    }
}

// ... (Remaining code)

1. TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers by Pete Warden and Daniel Situnayake.

2. Voice-Controlled Light Switch Project on Arduino Project Hub.

Feel free to reach out for any additional information or assistance!