Work

Speech to speech translation with translatotron: A state of the art review

Year: 2025

Type: article

Abstract: A speech-to-speech translation using cascade-based methods has been considered a benchmark for a very long time. Still, it is plagued by many issues, like the time to translate a speech from one language to another and compound errors. These issues are because cascade-based methods use a combination of other methods, such as speech recognition, speech-to-text transcription, text-to-text translation, and finally, text-to-speech transcription. Google proposed Translatotron, a sequence-to-sequence direct speech-to-speech translation model that was designed to address the issues of compound errors associated with cascade-based models. Today, there are 3 versions of the Translatotron model: Translatotron 1, Translatotron 2, and Translatotron 3. Translatotron1 is a proof of concept to demonstrate direct speech-to-speech translation. This first approach was found to be less effective than the cascade model, but it was producing promising results. Translatotron 2 was an improved version of Translatotron 1 with results similar to the cascade-based model. Translatotron 3, the latest version of the model, significantly improves the translation and is better than the cascade model at some points. This paper presents a complete review of speech-to-speech translation using Translatotron models. We will also show that Translatotron is the best model to bridge the language gap between African Languages and other well-formalized languages. • This article provides a comprehensive review of Translatotron, an end-to-end speech-to-speech translation model developed by Google. It explores the architecture, innovations, and performance of Translatotron compared to traditional cascaded systems. The review highlights its ability to preserve speaker identity and prosody while improving translation efficiency, positioning it as a significant advancement in the field of multilingual communication.

Source: Results in Engineering

DOI: 10.1016/j.rineng.2025.107780

Authors: Jules R. Kala, Emmanuel Adetiba, Abdultaofeek Abayomi, Oluwatobi E. Dare, Ayodele H. Ifijeh