6 datasets found

An end-to-end (E2E) speaker-attributed automatic speech recognition (SA-ASR) model was proposed recently to jointly perform speaker counting, speech recognition and speaker...

Speaker identification models are vulnerable to carefully designed adversarial perturbations of their input signals that induce misclas-sification.

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

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...