In a June 4, 2924 paper researchers from Google Research and Google DeepMind presented SimulTron, a model designed for on-device, real-time speech-to-speech translation (S2ST) built upon the Translatotron architecture.

The researchers highlighted the ongoing evolution of S2ST technology while emphasizing the persistent challenge of achieving accurate, real-time, on-device simultaneous translation. They noted that existing simultaneous translation models are not adequately optimized for the unique constraints of mobile devices, underscoring the significant challenge of achieving seamless real-time translation on mobile devices.

“Today, with smartphones and tablets being central hubs for personal and professional interactions, on-device S2ST is crucial,” they said.

In response to this challenge, they introduced SimulTron, a model that leverages the strengths of Translatotron while incorporating key modifications specifically tailored for the on-device, simultaneous translation scenarios.

Source: https://slator.com/assets/2022/03/logo.svg

Full article:https://slator.com/google-presents-first-on-device-real-time-speech-to-speech-translation-model/