One-shot learning of generative speech concepts

56 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Neural Voice Cloning with a Few Samples (2018, methodology): “In (Lake et al., 2014), a similar idea is modified to acoustic modeling task, with the goal of generating new words in a different language.”
Generalizing from a Few Examples (2019, background): “Apart from the early efforts on using FSL to recognize spoken words from one example [75], recent endeavors are on voice synthesis.”
DreamCoder: growing generalizable, interpretable knowledge with wake–sleep Bayesian program learning (2020, background): “Next we consider few-shot learning of probabilistic generative concepts, an ability that comes naturally to humans, from learning new rules in natural language ( 32 ), to learning routines for symbols and signs ( 5 ), to learning new motor routines for producing words ( 33 ).”