...Designing such a likelihood function is typically challenging; however, we observe that features like spectrogram are effective when latent variables have limited degrees of freedom. This motivates us to infer latent variables via methods like Gibbs sampling, where we focus on approximating the conditional probability of a single variable given the others.
Above is an excerpt from a paper I've been reading, and I don't understand what the author means by degrees of freedom of latent variables. Could someone please explain with an example, or add more details?
Shape and Material from Sound (31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA)