3 datasets found

Formats: JSON

Filter Results

  • WSJ0-mix dataset

    The WSJ0-mix dataset contains a min version of 2-, 3-, 4-, and 5-speaker mixtures simulated using clean speech in the WSJ0 corpus.

  • LJ Speech Dataset

    The LJ speech dataset is a dataset of speech samples recorded from a single speaker reading passages from 7 non-fiction books.

  • VCTK

    Voice conversion (VC) is a technique that alters the voice of a source speaker to a target style, such as speaker identity, prosody, and emotion, while keeping the linguistic...