The growing energy and performance costs of deep learning have driven the community to
reduce the size of neural networks by selectively pruning components. Similarly to their …

Multi-head self-attention is a key component of the Transformer, a state-of-the-art
architecture for neural machine translation. In this work we evaluate the contribution made …

We present a survey covering the state of the art in low-resource machine translation (MT)
research. There are currently around 7,000 languages spoken in the world and almost all …

Current research on spoken language translation (SLT) has to confront with the scarcity of
sizeable and publicly available training corpora. This problem hinders the adoption of neural …

Abstract Machine translation (MT) is a technique that leverages computers to translate
human languages automatically. Nowadays, neural machine translation (NMT) which …

The evaluation campaign of the 19th International Conference on Spoken Language
Translation featured eight shared tasks:(i) Simultaneous speech translation,(ii) Offline …

We present the Multilingual TEDx corpus, built to support speech recognition (ASR) and
speech translation (ST) research across many non-English source languages. The corpus is …

We present ESPnet-ST, which is designed for the quick development of speech-to-speech
translation systems in a single framework. ESPnet-ST is a new project inside end-to-end …

We seek to understand how the representations of individual tokens and the structure of the
learned feature space evolve between layers in deep neural networks under different …

Current research into spoken language translation (SLT), or speech-to-text translation, is
often hampered by the lack of specific data resources for this task, as currently available SLT …