rmuralin – Team D4 – Synesthesia

04May 2023 by rmuralin No Comments

Rachana’s Status Report for Apr 29

Personal Accomplishments This week, I was working on the UI functionality. I had alot of other commitments, so working on the recommendations was a little difficult. The integration for the three different modes of audio input work well so it allows me to record, search or upload a file. The MediaRecorder stream was fun to play around with. I want to currently work on getting recommendations based on the features of the song extracted on spotify, and display that for the user. We prefetch these songs for the user so in the event the user chooses to select these songs, it's going to be quick to get the signal parameters for the lighting engine. Testing wise, we tested for concurrency for user commands and main queue commands,…

04May 2023 by rmuralin No Comments

Parth’s Status Report for Apr 29

Parth, Weekly Status Reports

Personal Accomplishments This week I worked on finalizing the logic that converts signal processing outputs to commands to be executed by the lighting engine. I was able to implement change point detection to find out the locations at which the lights should do something different. Further, I was able to output various log files and dictionaries for different parts of the logic decisions: parameters, functions, and lights. These log files were useful in verifying the correctness of logic and are going to be used as a base for all the testing that we will be conducting from now until the demo. Further, I helped Rachana revamping the UI, and we were able to override execution commands. Finally, I also worked on the poster. On Track? Yes, I am on track…

04May 2023 by rmuralin No Comments

Team Status Report for Apr 29

Weekly Status Reports

Team Status Report for Apr 29 Summary This week, the team finished most of the development necessary for our project. We were able to get all our individual subsystems working and we were able to integrate them together. Next week, we are going to be completing our testing and optimization so that we are ready in time to demo our project the week after. Tests There were a various tests done on an individual subsystem level and at the project level throughout the development process. Signal Processing Song Recognition - We tested 15 different songs from Billboard’s top 100 playlist and the song recognition was able to accurately identify each of them with a 5 second clip Functionality Tests - Isolated individual features and tested them against a hand labeled…

22Apr 2023 by rmuralin No Comments

Rachana’s Status Report for Apr 22

Rachana, Weekly Status Reports

Personal Accomplishments This week I was mainly working on getting the signal parameters to match up with the beat time stamps, and implementing user feedback by process control switches. The user queue allows us to have real time feedback on our lighting interface, making it more user friendly. We are basically replacing the main commands at a beat timestamp with the user command that comes in, and then going on to process the rest of the user commands at the right places. I modified our spotify integration and feature query system to be like “I play a bit of the song”, or I can search up using the song name, or I can upload a song to test it, and the interface goes into Shazam recognizes the song…

22Apr 2023 by rmuralin No Comments

Parth’s Status Report for Apr 22

Uncategorized

Personal Accomplishments I worked on a couple of different components over the last two weeks. While I did not make much additional progress during the carnival week, I finished lighting logic. This involved writing the remaining functionality to select the different parameters for the light commands. I had to work with my teammates to redesign how the information will be packaged and relayed on to the lighting engine. While earlier we were thinking of making individual calls to the engine for every command, now I decided to split it up into multiple different arrays, each responsible for a different part of the command space: functions, lights, and parameters. Further, I spent a lot of time working on aligning the commands with the beat time stamps that posed new challenges as…

22Apr 2023 by rmuralin No Comments

Abhishek’s Status Report for Apr 22

Abhishek, Weekly Status Reports

Personal Accomplishments I spent the majority of this week helping with the lighting logic, working on testing functionality, and integrating components of the project together. In terms of the lighting logic, I was able to create the functionality for two main functions: the select_lights and the select_function functions. The select_lights function determines which lights in the gigbar2 will be activated for the upcoming lighting command. The logic behind this decision was based purely on the normalized energy values. It sets different thresholds of energy and depending on the energy threshold it determines how many lights and which lights should be activated. Ranking from lowest energy to highest energy we have. Lasers, laser+derbys, pars, pars and derbys, pars derbys and lasers, and finally all lights together. For the select_function function, I…

22Apr 2023 by rmuralin No Comments

Team Status Report for Apr 22

Weekly Status Reports

Summary We made a few decision changes to incorporate user feedback, and modified the granularity of values that we will extract. We were able to execute function calls every beat of the song. We are coming up with a clean approach on how to narrow down our function call space we can make for a certain time interval. We are working on a few small integrations with the UI as well to make it seamless. The new workflow for the project looks at playing a small snippet of a song using pyaudio by the user, have it recognized by the Shazam, and poll spotify for features, and get its MP3 version, and extract signal parameters for the entire song, playback the full song for the user, and execute commands from…

02Apr 2023 by rmuralin No Comments

Team Status Report for April 1st, 2023

Weekly Status Reports

April 1, 2023 Team Status Report for April 1 Summary Our team continued to make significant progress towards our project goals. Last week, we were able to narrow down our subset of features in the signal processing subsystem and test some of these features. Throughout our testing, we realized that some features such as the MFCC and the liveness were not adding much more new information to our analysis, so we decided to shelf them for the meantime. This allowed us to focus on the impact of features such as frequency, amplitudes, and beat detection, which we were able to use to make decisions about the colors, intensity, and timing of the lights respectively. These decisions proved beneficial while determining the lighting logic, and we were able to make significant…

02Apr 2023 by rmuralin No Comments

Parth’s Status Report for April 1

Parth, Weekly Status Reports

Personal Accomplishments Most of my time this week went towards working on integrating the signal processing subsystem with the lighting engine. I worked extensively on defining the logic which we will be using to convert signal processing attributes to lighting calls. I collaborated with my teammates on the necessary adjustments and refinements to the lighting logic, and we were able to finalize the lighting effects for our show. I also spent time coming up with metrics to test smaller chunks of the functionality, and helped develop audio tracks for the interim demo. Additionally, I worked on creating documentation for my subsystem, making sure it was well-documented and easy to understand for any future developers who may work on the project. On Track? While I was able to meet all my…

02Apr 2023 by rmuralin No Comments

Rachana’s Status Report for April 1st, 2023

Rachana, Weekly Status Reports

Personal accomplishments After a lot of deliberation,we decided to remove certain features that were not affecting our audio signals as much. I thought alot about the use of MFCC as well, and I don't think that was adding as much value as isolating frequencies. So, the newer approach to chunk these dataframes is to use peak frequencies, beat detection, and amplitudes. We also thought about isolating parts of the chorus, but quickly realized that amplitudes are reflective of While combining these with global parameters, we can see that this gives us quite a bit of information to work off of. This was a necessary reduction in the number of features because we were getting a bit of relevant information. We also increased the resolution of the graphs to incorporate values…