Search Results for author:
Found 3 papers, 1 papers with code
N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses
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.
Comparing Writing Styles using Word Embedding and Dynamic Time Warping
The development of plot or story in novels is reflected in the content and the words used.
Making Sense of Hidden Layer Information in Deep Networks by Learning Hierarchical Targets
This paper proposes an architecture for deep neural networks with hidden layer branches that learn targets of lower hierarchy than final layer targets.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
