Work

End-to-end Speech Translation with Self-supervised Speech Representations

Year: 2020

Type: dissertation

Abstract: For years speech translation has been faced as concatenation of speech recognition and machine translation. The powerful architectures of deep learning has made end-to-end speech translation feasible. The student will have to use the encoder-decoder architecture based on Transformer to build multilingual speech translation systems.

Source: LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)

Authors: Gallego Olsina, Gerard Ion

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W3114608346

Cites: 46

Cited by:

Related to: 10