Spoken language identification refers to the task of automatically predi...
In the recent years, speech representation learning is constructed prima...
Speech representation learning approaches for non-semantic tasks such as...
Data scarcity is a crucial issue for the development of highly multiling...
We introduce FLEURS, the Few-shot Learning Evaluation of Universal
Repre...
We introduce XTREME-S, a new benchmark to evaluate universal cross-lingu...
We summarize the results of a host of efforts using giant automatic spee...
Building ASR models across many language families is a challenging multi...
Streaming end-to-end automatic speech recognition (ASR) models are widel...