Google gives progress report on its Universal Speech Model

In November, Google announced that it was embarking on an initiative that would culminate in the development of a machine-learning model capable of recognizing and translating 1,000 of the world's most spoken languages. Over the past several months, the company has been working toward that goal and has published a blog entry by members of the team working on the project. The team at Google has also published a paper describing the introduction of its Universal Speech Model (USM) on the arXiv pre-print server.