It is challenging to extract semantic meanings directly from audio signa...
In this paper, the minimization of the weighted sum average age of
infor...
As large and powerful neural language models are developed, researchers ...
Large pretrained language models (LMs) like BERT have improved performan...
Speaker attribution is required in many real-world applications, such as...
We propose a novel Transformer encoder-based architecture with syntactic...
Deep speaker embedding models have been commonly used as a building bloc...
Abbreviation disambiguation is important for automated clinical note
pro...
Speaker embedding models that utilize neural networks to map utterances ...