Towards Robust End-to-End Speech Translation
Noisy inputs in Speech Recognition causes performance to drop, the same is happening for the more complex case of Speech Translation. We want to explore speech enhancement techniques in a multi-task setting for end-to-end speech translation
| Autor: | |
|---|---|
| Formato: | tesis de maestría |
| Fecha de publicación: | 2020 |
| País: | España |
| Recursos: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/330400 |
| Acesso em linha: | https://hdl.handle.net/2117/330400 |
| Access Level: | acceso abierto |
| Palavra-chave: | Speech Translation End-to-End ST NMT Translation Artificial Intelligence Traducción Inteligencia artificial traducción automática Extremo a extremo Intel·ligència artificial -- PFC Traducció automàtica -- PFC |
| Resumo: | Noisy inputs in Speech Recognition causes performance to drop, the same is happening for the more complex case of Speech Translation. We want to explore speech enhancement techniques in a multi-task setting for end-to-end speech translation |
|---|