The advancement of speech technologies has been remarkable, yet its
inte...
Speech recognition applications cover a range of different audio and tex...
We introduce XTREME-S, a new benchmark to evaluate universal cross-lingu...
This paper presents XLS-R, a large-scale model for cross-lingual speech
...
The scale, variety, and quantity of publicly-available NLP datasets has ...
Automatic speaker verification systems are vulnerable to audio replay at...
Traditional automatic speech recognition (ASR) systems often use an acou...