Personal Accomplishments
I went over the design report that had a lot of feedback for the signal processing section, and I worked on the Ethics assignment that allowed me to examine ethical considerations behind our project a little more. With respect to the design report, there were a few concerns on sampling rate that I had to address. With the default sampling rate being 44.1KHz. Since we are chunking and never really outputting the audio itself, we don’t care about the end result of the audio, but we care about the statistics we are able to generate from the audio. Moreover, I realized that in the design report, there were way too many features I wanted to iterate over for a data frame for a singular chunk. I realized that it is more important to keep a select number of features that have a direct correlation with lighting, and then expand the feature set as I go on. The features that I am currently working on are going to be around 4 along with the standard deviations mean and median values in pitch and amplitudes. Beat detection where the song can be detected using tempo analysis. Mapping this to a lighting change will be easy because we can synchronize light deflections to the beat of the music.
Moreover, frequency analysis using the pitch spectrograms will be useful as we can use different colors to determine different frequency bands and we can map these lighting changes accordingly. The spectral centroid of an audio signal corresponds to its “brightness” or “tonality”. This can be extracted using techniques such as spectral centroid analysis. Mapping this to lighting changes could involve using different colors or brightness levels to represent different spectral centroids. MFCCs are a commonly used feature in audio signal processing and can be used to capture the timbral characteristics of a sound. Mapping this to lighting changes could involve using different colors or patterns to represent different MFCC values.
On Track?
I am mostly on track with my work. I might need to put in some additional time next week to get a head start on the integration. I will be able to finish it up in time for integration
Goals for Next Week
For now, I want to focus on chunking stuff for a single song, and then integrating it with the Ui and light systems. Further, we also need to spend some time collectively next week to plan out the lighting logic that will convert the inputs from the signal processor to the desired light outputs.