|67||Sound Controlled Smoke Detector
| Almost all of us encounters false fire alarms at some point in our life. Although many modern fire alarms have the ability to mute temporarily with a push of button, the physical location of the smoke detector does not always make it easy to do so.
At the same time, voice controlled products are entering markets, and gaining popularity in recent days. These products, such as Android phones and Amazon Echo, can be activated by keyword such as “OK Google”, ”Alexa”, or “Amazon”.
Therefore, we propose a sound controlled fire alarm that allows you to easily turn the alarm off by shouting the keyword "cooking" when false alarm happens (in addition to a push button). The project will contain two parts: 1) a smoke alarm circuit with carbon monoxide sensor, microphone, mute button, and 2) a DSP core for the key word recognition.
The user will need to train the alarm once, where the DSP will find and store the Mel-Frequency Cepstral Coefficients (MFCCs) for the training word. Then once the alarm is triggered, interrupt will be served to the core through a interrupt pin or a GPIO, and the DSP will actively listen for any keywords, finding the MFCCs for what it hears, and comparing with the stored MFCCs. If the mean square error is below a threshold, the DSP will stop the alarm.
In additional, if we have time, we may also look into Dynamic Time Warping (DTW) to improve our accuracy.