Add Free Universal Sound Separation (FUSS) Dataset

🚀 Feature

Add the FUSS dataset to pytorch.datasets.

Motivation

While Pytorch Audio contains a variety of clean speech datasets, it does not contain any noise samples or room impulse response samples, making the setup of problems in speech or audio separation (or simply training recognition in the presence of noise/reverb) harder.
This dataset will potentially be well supported and used, as it is part of DCASE 2020

Pitch

Implement this under torchaudio.datasets, exposing a very similar API to existing datasets. Both ssdata (dry) and ssdata_reverb (reverberated) should be implemented, potentially as different functions.

Alternatives

An alternative would be adding separate datasets for noise samples (e.g. NoiseX-92 if licensing permits) and room impulse responses, in a format that allows for easy mixing by the user into train/validation/test sets, combined with the existing speech datasets already available in the API.

Start in torchaudio.datasets by comparing the existing dataset APIs, then read the linked FUSS license documentation and dataset details. Implement access for both ssdata (dry) and ssdata_reverb (reverberated), with behavior consistent with existing datasets; done means both variants are exposed through the datasets API.