Spoken language identification refers to the task of automatically predi...
We introduce the Universal Speech Model (USM), a single large model that...
Much of text-to-speech research relies on human evaluation, which incurs...
We present FRMT, a new dataset and evaluation benchmark for Few-shot
Reg...
We introduce FLEURS, the Few-shot Learning Evaluation of Universal
Repre...
In this paper we share findings from our effort to build practical machi...
We introduce XTREME-S, a new benchmark to evaluate universal cross-lingu...
We present mSLAM, a multilingual Speech and LAnguage Model that learns
c...
Unsupervised pre-training is now the predominant approach for both text ...
State-of-the-art multilingual models depend on vocabularies that cover a...
Transformer-based models have achieved stateof-the-art results in many t...
The recently proposed massively multilingual neural machine translation ...
We propose a practical scheme to train a single multilingual sequence
la...
We address fine-grained multilingual language identification: providing ...
Neural Machine Translation (NMT) is an end-to-end learning approach for
...