Audio Generation - Groups

TIMIT

The TIMIT corpus is a widely used benchmark for speech recognition tasks. It contains 3,696 training utterances from 462 speakers, excluding the SA sentences. The core test set...

Dataset
JSON

D-Flow: Differentiating through Flows for Controlled Generation

The dataset used in the paper D-Flow: Differentiating through Flows for Controlled Generation

Dataset
JSON

S3VAE: Self-Supervised Sequential VAE

A sequential variational autoencoder for sequential data, including videos and audios, with self-supervision and regularization.

Dataset
JSON

3 datasets found

TIMIT

D-Flow: Differentiating through Flows for Controlled Generation

S3VAE: Self-Supervised Sequential VAE