Shulou(Shulou.com)12/24 Report--

CTOnews.com, December 2, Google issued a press release today, officially introducing the launch of a new AI model called Translatotron 3, which can achieve simultaneous interpretation of voice to speech without any parallel voice data.

Google launched Translatotron S2ST in 2019, launched its second version in July 2021, and announced in a paper released on May 27, 2023 that it was deploying new methods to train Translatotron 3.

According to the researchers, Translatotron 2 already provides excellent translation quality, speech robustness (Robust) and speech naturalness, while Translatotron 3 implements "the first completely unsupervised end-to-end model of direct speech to speech translation".

Traditionally, S2ST is solved by the cascade method of automatic speech recognition, machine translation and text-to-speech synthesis, but Translatotron 3 relies on a novel end-to-end architecture to directly map the source language speech to the target language without relying on the intermediate text representation.

The Translatotron 3 model can also be used to create tools to help people with language barriers, or to develop more attractive and effective personalized language learning tools.

The official press release address is attached to CTOnews.com, which can be read in depth by interested users.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.