Albert Sanchís

Real-Time One-Pass Decoder for Speech Recognition Using LSTM Language Models

2019

Recurrent Neural Networks, in particular Long-Short TermMemory (LSTM) networks, are widely used in Automatic Speech Recognition for language modelling during decoding,usually as a mechanism for rescoring hypothesis. This paperproposes a new architecture to perform real-time …

Europarl-ST: A Multilingual Corpus for Speech Translation of Parliamentary Debates

2020

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 datasets are restricted to a limited set of …