4 datasets found

Formats: JSON Tags: speech separation

Filter Results

  • Explainable Deep Clustering for Monaural Speech Separation

    The proposed X-DC model uses a dataset of mixed speech signals of two, four, or eight speakers.

  • LibriMix

    The LibriMix dataset is a large corpus of mixed speech, designed for training and evaluating speech separation systems.

  • LRS2

    The LRS2 dataset consists of 48,164 video clips from outdoor shows on BBC television. Each video is accompanied by an audio corresponding to a sentence with up to 100 characters.

  • WHAM!

    The WHAM! dataset is used for testing the proposed Bayesian factorised speaker-environment adaptive training and test time adaptation approach for Conformer models.
You can also access this registry using the API (see API Docs).