6 datasets found

The VoxCeleb dataset is a large-scale speaker identification dataset, used to evaluate the performance of face recognition systems.

VoxCeleb: A Large-Scale Speaker Identification Dataset

Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persisting challenge. In this paper, we propose a new...

Speaker verification (SV) is a task aiming at identifying the true characteristics of a speaker and accepting or discarding the identity claimed by the speaker.

Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature...

Speaker recognition aims to identify speaker information from input speech. A type of speaker recognition is speaker verification (SV). It determines whether the test speaker's...