research
∙
05/04/2023
End-to-end spoken language understanding using joint CTC loss and self-supervised, pretrained acoustic encoders
It is challenging to extract semantic meanings directly from audio signa...
share
research
∙
05/06/2022
How to Minimize the Weighted Sum AoI in Multi-Source Status Update Systems: OMA or NOMA?
In this paper, the minimization of the weighted sum average age of infor...
research
∙
02/25/2022
On the data requirements of probing
As large and powerful neural language models are developed, researchers ...
research
∙
01/27/2022
Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation
Large pretrained language models (LMs) like BERT have improved performan...
research
∙
02/06/2021
Speaker attribution with voice profiles by graph-based semi-supervised learning
Speaker attribution is required in many real-world applications, such as...
research
∙
12/21/2020
Encoding Syntactic Knowledge in Transformer Encoder for Intent Detection and Slot Filling
We propose a novel Transformer encoder-based architecture with syntactic...
research
∙
05/22/2020
Speaker diarization with session-level speaker embedding refinement using graph neural networks
Deep speaker embedding models have been commonly used as a building bloc...
research
∙
12/12/2019
Training without training data: Improving the generalizability of automated medical abbreviation disambiguation
Abbreviation disambiguation is important for automated clinical note pro...
research
∙
02/06/2019