John Vinyard
@johnvinyard.bsky.social
Working on sparse, interpretable, and easy-to-manipulate models of audio (especially music).
https://github.com/JohnVinyard
https://github.com/JohnVinyard
You can play with this example yourself here: blog.cochlea.xyz/resonancemod...
Extracting Playable Instrument Models from Short Audio Examples
blog.cochlea.xyz
November 13, 2025 at 9:11 PM
You can play with this example yourself here: blog.cochlea.xyz/resonancemod...
You can play with it too: blog.cochlea.xyz/conv-instrum...
Hand-Controlled WebAudio Instrument
blog.cochlea.xyz
October 18, 2025 at 4:00 PM
You can play with it too: blog.cochlea.xyz/conv-instrum...
I have received an endorsement! Feel free to read the paper and provide feedback if you're so inclined!
May 8, 2025 at 4:23 PM
I have received an endorsement! Feel free to read the paper and provide feedback if you're so inclined!
Here's the "dashboard" for a model that's training right now. Event times are represented bottom-left, and event vectors, which encode everything about the sound _except_ for time-of-occurrence, on the bottom-right.
March 27, 2025 at 2:09 PM
Here's the "dashboard" for a model that's training right now. Event times are represented bottom-left, and event vectors, which encode everything about the sound _except_ for time-of-occurrence, on the bottom-right.
To put it into context, an encoder model is trained to incrementally decompose a segment of audio into some number of event vectors and their times-of-occurrence. You can read more about the training process here:
blog.cochlea.xyz/sparse-inter...
blog.cochlea.xyz/sparse-inter...
Toward a Sparse Interpretable Audio Codec
blog.cochlea.xyz
March 27, 2025 at 2:05 PM
To put it into context, an encoder model is trained to incrementally decompose a segment of audio into some number of event vectors and their times-of-occurrence. You can read more about the training process here:
blog.cochlea.xyz/sparse-inter...
blog.cochlea.xyz/sparse-inter...