16th March, 2014


A few updates about the work for last week :

1. We are able to extract features of the audio using the LibXtract library now. As of now we are just doing it using a .wav file on the phone. We are trying to extend it to microphone input

2. We have completed implementing online training (using just FFT). In online training, we create a database of different sounds and store them on the smartphone using SharedPreferences. Everytime a new signal arrives, it is compared with the stored files and if there’s a match, then the appropriate action.

10th March, 2014


The classification using FFT is complete. We calculate the peak frequency at every instance and if it lies within a band we defined earlier, then we know that it COULD be one of the pre-defined sounds. We maintain a counter for each band which is incremented every time there’s a frequency component that exceeds a pre-defined threshold. That way, we can minimize the chances of false alarms. 

Spectrum of Fire AlarmThe spectrum of Fire Alarm, as we stated during the presentation was centred around 3.62kHz. Every time this frequency crosses a certain threshold, we increment a counter. Once the counter reaches a certain threshold, we can classify the signal as required.

8th March, 2014


The classification can be done using the Visualizer class in Android. Using the getFft() function of the Visualizer class, we can get the FFT of the incoming signal. Since we know beforehand that the signals we are trying to classify have peaks in different bands of frequencies, a simplistic way of the classification would be to classify them just based on the peaks of the frequency.

1st March, 2014


The porting of the audio feature extraction library is almost complete. We will begin the testing of the library once its completed. 

Apart from this. we are adding multiple features to our for the hearing impaired. One of the features we have added is adding an activity for speech to text and text to speech to assist the hearing impaired to be able to communicate with people.