2019 Projects
| Project 1 | Project 2 | Project 3 | Project 4 | Project 5 | Project 6 | Project 7 |
|---|---|---|---|---|---|---|
Error creating thumbnail: Unable to save thumbnail to destination |
Error creating thumbnail: Unable to save thumbnail to destination |
Error creating thumbnail: Unable to save thumbnail to destination |
Error creating thumbnail: Unable to save thumbnail to destination |
Error creating thumbnail: Unable to save thumbnail to destination |
Error creating thumbnail: Unable to save thumbnail to destination |
Error creating thumbnail: Unable to save thumbnail to destination |
Harmoni-US
By Twisha Sundararajan, Megan Wei, Maya Itty
Project Description: Our product recognizes chords from a voice or an instrument and generates real-time harmony to the melody presented based on the key. Using PD to detect the pitch, we transpose it a specific amount of semitones in order to create a minor and major chord based off a single pitch.
Mooderater
By Megan Peng, Carol Tu
Project Description: The Mooderater will monitor and classify brain waves as either alpha or beta by measuring their frequencies. The user will select whether they would like to focus or relax, and in response, the Mooderater will play customized music that will enhance either alpha or beta waves, which will either improve concentration or reduce stress, based on the dominant wave. Alpha waves have a low frequency, with a range of 8 to 12 Hz, and they elevate levels of serenity; meanwhile, beta waves have a higher frequency, ranging from 12 to 32 Hz and heightens attentiveness and problem solving abilities.
Musiciser
By Tevin Wang, Austin Wang, Doyoon Kim
Project Description: Are you an athlete? Do you listen to music while you exercise/workout? Musiciser is the perfect app for you! Musiciser is an app that allows you to not only listen to music while running but also helps you keep a consistent pace. First, you can upload the music of your choice onto the application. Next, you can set the intensity of your exercise from the range of light to vigorous -- we call this the ExerciseTempo. Lastly, you can start musicizing or exercising with the app, but know that if you are running behind your set desired pace, the music will slow down in real time corresponding to how far you are behind your pace and the pitch will also become distorted in real time. If you prefer not to listen to distorted pitches, there is also an option to preserve the pitch of the audio file no matter how slow it becomes in real time. This app is designed to motivate you to move at a constant speed by manipulating your hearing sense to send a warning of your unconscious laziness (if it happens) so you can fully enjoy the music that the wonderful musical stars of today have released. Start exercising at your tempo today!
piLED
By Teresa He, Lia Seo, Sophia Yu
Project Description: PiLED is a program developed with Pure Data and Python that composes a melody and displays the beat by using LED lights. Through PD, the user will be able to provide a tempo for the program, which will correspond with the lights’ actions. In addition, piLED will create the melodies by using markov chains: models that use probability to create sequences.
Transform-A-Tune
By Natalie Brewer, Rupali Sarathy, Yuhan Chen
Project Description: This application allows a user to input a melody of their choice and choose a conversion in order to create a brand new melody. Transform-A-Tune utilizes the process of reflections and mathematical algorithms in order for brand new melodies to be discovered. Some conversions include a negative harmony, a symmetric harmony, reversing the pitches of the melody, randomizing the pitches in the melody, and stretching the relationships between pitches of the melody.
GANmidi
By Conan Lu, Elena Atluri, Satvik Nagpal
Project Description: Our project aims to convert music into a given style using machine learning. We accomplished this using an algorithm known as a generative adversarial network (GAN). A GAN consists of a generator, which creates music based on an input, and a discriminator, which judges if the generated music is real or fake. We fed in pairs of pitch classes and piano rolls to train the algorithm in a given style. Then, the trained generator can be used to interpret other musical pieces into the style it was trained on.
VisAudio
By Alson Chan, Leo Yang, Aniketh Prasad
Project Description: Our project aims to help deaf people by taking in audio / midi input and comparing it to a midi file. With these comparisons, we can display the audio using objects and colors and can give feedback to the user, detecting wrong notes and other problems with playing. Furthermore, we plan to have a synesthesia type object that displays the current pitch and note that the user is playing in a piano-type interface.