sWuggy
A zero-shot spoken language understanding evaluation task used to test the lexical-level linguistic knowledge acquired by speech models.
Timeline (last 90 days)
On the three tasks sWuggy, sBLIMP, and tSC, GSLM2 narrows the gap between speech models and text models by about two orders of magnitude.
The sWuggy task examines lexical and phonological knowledge, requiring the model to judge which of a real pseudoword and a nonword with one phoneme changed is more like a real word.
All Facts (2)
On the three tasks sWuggy, sBLIMP, and tSC, GSLM2 narrows the gap between speech models and text models by about two orders of magnitude.
50%UnverifiedThe sWuggy task examines lexical and phonological knowledge, requiring the model to judge which of a real pseudoword and a nonword with one phoneme changed is more like a real word.
50%