Difference between revisions of "DUMMY PROTOTYPICAL NETWORKS FOR FEW-SHOT OPEN-SET KEYWORD SPOTTING: abstract simplified (18062976)"
Wikipatents (talk | contribs) (Creating a new page) |
Wikipatents (talk | contribs) (Creating a new page) |
||
Line 1: | Line 1: | ||
− | In this abstract, the authors describe a system and technique for processing audio data. They propose a method called few-shot open-set keyword spotting (FSOS-KWS) using a dummy prototypical network. The process involves determining prototype representations based on support samples associated with different classes. | + | In this abstract, the authors describe a system and technique for processing audio data. They propose a method called few-shot open-set keyword spotting (FSOS-KWS) using a dummy prototypical network. The process involves determining 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 determined in the same learned metric space as the prototype representations. Distance metrics are calculated for query samples using 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. |
Latest revision as of 16:20, 1 October 2023
In this abstract, the authors describe a system and technique for processing audio data. They propose a method called few-shot open-set keyword spotting (FSOS-KWS) using a dummy prototypical network. The process involves determining 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 determined in the same learned metric space as the prototype representations. Distance metrics are calculated for query samples using 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.