Real-world signals change over time, so fixed filters need adaptation

Evidence

Digital filters with constant coefficients are an efficient and flexible approach for modelling LTI systems and signals. However, real world signals and systems can change their parameters as a function of time. There is a need for signal processing systems and algorithms that are able to adapt to changing conditions, or that are able to learn or can be trained to behave in a desired manner. — Ville Pulkki, Matti Karjalainen, Communication Acoustics- An…, 440