Planet Symphony

GIF
GIF

Created for DurHack 2026 with the theme of "Composition"!

alien decal

We were also heavily inspired by QRTs Challenge "Information Hidden in Plain Sight" as well as Marshall Waces "New Worlds".

planet reciever

alien decal

Inspiration

What do you think of when you hear the word "Composition"? Our team is heavily comprised with musicians so we immediately thought of music composition! We then thought, surely we can hide data inside of some cute midi tunes! Additionally we caught a brainworm about "New Worlds" and The Arecibo messages (https://en.wikipedia.org/wiki/Arecibo_message) and were inspired by "My Singing Monsters" to have the music produced by the singing aliens of "Planet Symphony" and transmitted via the vacuum of space to "Planet New'Wave'O".

There are many methods of data transfer, however the majority have one idea in mind: efficiency. In a world where there is more data in transit than ever before, why not send messages purely through song? And completely connectionless!

What it does

Planet Symphony begins with a message (plaintext) and a choice of key and musical scale (e.g., F# major-pentatonic). Next, that message is encoded algorithmically into a melody within a set of configurated parameters (cluster size, octaves). This melody is then sent to the Transmitter for a waiting receiver to hear. The waiting Receiver is a trained model for identifying musical notes, which is then passed into the algorithmic decoder. As the encoder is deterministic, as long as no notes are missed by the receiver the original message should be decoded with zero error.

during encoding a specific music scale is chosen (demo uses f# major pentatonic) and only those notes are selected from so all notes are diatonic (in the specified key). when encoding characters to musical phrases, smaller intervals are prefered to sound more scalic. a drone note of the root is used to add a grounding tone and allow melodies to be properly parsed by your ears. paired with a specific pattern of cortchets and quavers the melody sounds more organic and pleasant.

planet_sender

How we built it

We distributed the different areas of the project to different members of the team, with a broad focus for each of us:

Malachi: creating the data encoding / decoding system
Jack: creating the receiver and linking it to the decoder
Sarunas: creating the transmitter and linking it to the encoder
Matty: Creating the visual assets and fronting the GUI

The main technologies used:

Python
Pygame
Pytorch
Music Theory!

Challenges we ran into

Receiver model

We could not train the Receiver model until we had the Transmitter mostly working, which meant parallel working was limited. The architecture for the receiver model can be seen below, with a CNN analysing spectrogramic images The workflow can be seen below, for the entire network itself. The CNN operates in the middle, and the decoder and encoder stages that were algorithmic operate on either side in real time.
Linking together the different parts was only possible later in the pipeline, which lead to a few issues connecting the modules
The receiver was limited with note sustain, which mean the melody's notes needed clear distinction which limited the choices in the sound.

Accomplishments that we're proud of

Malachi: Creating a deterministic encoder and decoder which can effectively translate messages into song and back to messages. Sarunas: Translating the notes into a song and having it actually sound good. Matty: Creating a visual language to fit with the project Jack: Training a CNN to accurately read a spectrogram and improving accuracy from pure audio analysis.