So this week we had to finalize the information for our proposal presentation, which we all worked on collectively. My main focus was on posture analysis, so I worked on what technical challenges we would face when it comes to posture regarding good singing posture. However, after our presentation, we were faced with the complexity of real-time analysis which when coupled with latency becomes more difficult to handle within the time frame that we currently have for our project.
Therefore we had to pivot our analysis and focus on a lesson-based composition. Because of that, I spent most of this week looking into musical exercises and the music theory that we consider important to start out music lessons for beginners. I worked on narrowing down the scale for lessons to just the major scale to reduce the complexity we would have to work on with other scales (minor -> natural, harmonic, etc)
Team Status Report for 2/27/2021
One major risk that we can potentially face at this point of the project is having diverging ideas of our project due to working on our individual components without integration in mind, which can cause us problems down the road. A problem we are actively solving now is clearly defining our project scope and goals. After our proposal presentation, we pivoted from a real-time feedback singing coach to one that provides feedback after a performance. This change was brought on by the difficulty of balancing pitch analysis and reasonable latency constraints to allow for real-time feedback. Our project now focuses on providing lessons in different singing aspects, namely: pitch accuracy, timing, and music theory. We have also made song performance analysis a stretch goal for our project, which used to be a core feature.
These changes in project goals and scope have prompted us to re-evaluate our project schedule, something that we are still updating as we continue to enumerate the aspects of our updated project. We have been meeting more than usual this week (5 instead of 4 times, for 1-2 hours) to address the changes in our project. We documented our pivot ideas in this document here:
https://docs.google.com/document/d/1hAuto5vd_O6j6cV3cd6imi2Ym6Bqz51UVvyWXM9Fn9g/edit?usp=sharing
As we are now taking a more lesson based approach, we are in the process of crafting lessons to help train users in the aspects of singing mentioned above. We are considering using a phonetograph to analyze users’ vocal ranges upon signup and compute it after good performance in several lessons to measure progress over time. After signup, they will go through a range of pitch exercises and rhythm exercises. Posture analysis is also no longer being provided in real time, but after the lessons as a part of the performance report.
We designed the integration and flow of this new lesson based approach as a rough draft which can be found below:
Funmbi’s Status Report : 2/20/2021
So far we have been working on fine tuning our product, and inspecting the metrics we would like our software to cater to for the user. We have completed the abstract and finished the slides for our proposal. After the last 2 meetings with a professor and TA we have a baseline for our project and are currently researching the most effective approach. The work has been divided based on our skills and I am currently working on how to use the open pose library for the posture detection. This week I am going to be collating data sets for the posture detection for testing and thinking of ways to detect posture with the microphone in the way, which was an issue raised by my group.
In addition I also need to think on how to integrate the database to the web application as well as finding songs that would be our base exercises for the users as well as test cases. Basically a lot of this week and the upcoming week is on research, and finding the software that would be preferable for the product and how to integrate it to fit the user experience.