Speech to Speech Translation with Translatotron: A State of the Art Review
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917929699770368 |
|---|---|
| author | Kala, Jules R. Adetiba, Emmanuel Abayom, Abdultaofeek Dare, Oluwatobi E. Ifijeh, Ayodele H. |
| author_facet | Kala, Jules R. Adetiba, Emmanuel Abayom, Abdultaofeek Dare, Oluwatobi E. Ifijeh, Ayodele H. |
| contents | A cascade-based speech-to-speech translation has been considered a benchmark for a very long time, but it is plagued by many issues, like the time taken to translate a speech from one language to another and compound errors. These issues are because a cascade-based method uses a combination of methods such as speech recognition, speech-to-text translation, and finally, text-to-speech translation. Translatotron, a sequence-to-sequence direct speech-to-speech translation model was designed by Google to address the issues of compound errors associated with cascade model. Today there are 3 versions of the Translatotron model: Translatotron 1, Translatotron 2, and Translatotron3. The first version was designed as a proof of concept to show that a direct speech-to-speech translation was possible, it was found to be less effective than the cascade model but was producing promising results. Translatotron2 was an improved version of Translatotron 1 with results similar to the cascade model. Translatotron 3 the latest version of the model is better than the cascade model at some points. In this paper, a complete review of speech-to-speech translation will be presented, with a particular focus on all the versions of 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05980 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Speech to Speech Translation with Translatotron: A State of the Art Review Kala, Jules R. Adetiba, Emmanuel Abayom, Abdultaofeek Dare, Oluwatobi E. Ifijeh, Ayodele H. Computation and Language Artificial Intelligence A cascade-based speech-to-speech translation has been considered a benchmark for a very long time, but it is plagued by many issues, like the time taken to translate a speech from one language to another and compound errors. These issues are because a cascade-based method uses a combination of methods such as speech recognition, speech-to-text translation, and finally, text-to-speech translation. Translatotron, a sequence-to-sequence direct speech-to-speech translation model was designed by Google to address the issues of compound errors associated with cascade model. Today there are 3 versions of the Translatotron model: Translatotron 1, Translatotron 2, and Translatotron3. The first version was designed as a proof of concept to show that a direct speech-to-speech translation was possible, it was found to be less effective than the cascade model but was producing promising results. Translatotron2 was an improved version of Translatotron 1 with results similar to the cascade model. Translatotron 3 the latest version of the model is better than the cascade model at some points. In this paper, a complete review of speech-to-speech translation will be presented, with a particular focus on all the versions of 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. |
| title | Speech to Speech Translation with Translatotron: A State of the Art Review |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.05980 |