We propose a method of separating a desired sound source from a
single-c...
Learning to recognize new keywords with just a few examples is essential...
User studies have shown that reducing the latency of our simultaneous le...
With the rise of low power speech-enabled devices, there is a growing de...
We propose the Fréchet Audio Distance (FAD), a novel, reference-free
eva...
Low power digital signal processors (DSPs) typically have a very limited...
Existing music recognition applications require a connection to a server...