Memory-based signal source separation and categorization
This project performs signal analysis to drive desired signal-triggered actions, grouping, categorizing, and stratifying signals into useful buckets. It addresses shortcomings of blind source separation, which repeatedly guesses at sources and labels them as brand new, by keeping a memory of previously identified sources so distinctions persist across samples, analogous to how humans can tell pianos from drums and remember the distinction across songs.
What it addresses
Blind source separation continuously guesses at sources and labels them as brand new instead of having a memory of previously identified sources.
Shared over time
Each entry reflects what was shared on that date. Details may have changed since then.
Memory-based signal source separation and categorization
This project performs signal analysis to drive desired signal-triggered actions, grouping, categorizing, and stratifying signals into useful buckets. It addresses shortcomings of blind source separation, which repeatedly guesses at sources and labels them as brand new, by keeping a memory of previously identified sources so distinctions persist across samples, analogous to how humans can tell pianos from drums and remember the distinction across songs.
Problem: Blind source separation continuously guesses at sources and labels them as brand new instead of having a memory of previously identified sources.
Posted by @gabinator · Original comment ↗
“Signal analysis to drive <desired signal-driven action>. Grouping/categorizing/stratifying signals into useful buckets to drive actions. Blind source separation has drawbacks like continuously guessing at sources and labeling them as brand new instead of having a memory of previously identified sources. Think of how humans can distinguish pianos from drums and remember the distinction across songs.”