DUMMY PROTOTYPICAL NETWORKS FOR FEW-SHOT OPEN-SET KEYWORD SPOTTING: abstract simplified (18062976)

In this abstract, a system and technique for processing audio data is described. Specifically, a method called few-shot open-set keyword spotting (FSOS-KWS) is introduced. The process involves creating prototype representations based on support samples associated with different classes. Each prototype representation is linked to a specific class. Additionally, a dummy prototype representation is created in the same metric space as the prototype representations. Distance metrics are then determined for query samples using both the prototype representations and the dummy prototype representation. Based on these distance metrics, each query sample is classified into one of the classes associated with the prototype representations or into an open-set class associated with the dummy prototype representation.