no code implementations • 29 Jun 2022 • Jesús Andrés-Ferrer, Dario Albesano, Puming Zhan, Paul Vozila
In this work, we propose a contextual density ratio approach for both training a contextual aware E2E model and adapting the language model to named entities.
no code implementations • 29 Jun 2022 • Dario Albesano, Jesús Andrés-Ferrer, Nicola Ferri, Puming Zhan
In contrast to some previous works, our results show that Transformer does not always outperform LSTM when used as prediction network along with Conformer encoder.