N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses

1 code implementation • ACL 2021 • Karthik Ganesan, Pakhi Bamdev, Jaivarsan B, Amresh Venugopal, Abhinav Tushar

In our work, we test our hypothesis by using concatenated N-best ASR alternatives as the input to transformer encoder models, namely BERT and XLM-RoBERTa, and achieve performance equivalent to the prior state-of-the-art model on DSTC2 dataset.

Spoken Language Understanding