Since Large Language Models or LLMs have demonstrated high-quality
perfo...
Spotting user-defined/flexible keywords represented in text frequently u...
Using audio and text embeddings jointly for Keyword Spotting (KWS) has s...
DNN pruning is a popular way to reduce the size of a model, improve the
...
Model parameter regularization is a widely used technique to improve
gen...
Streaming keyword spotting is a widely used solution for activating voic...
This paper explores the possibility of using visual object detection
tec...
Voice trigger detection is an important task, which enables activating a...
Deep neural network (DNN) model compression for efficient on-device infe...
Neural Architecture Search (NAS) is a powerful tool to automatically des...
Neural Architecture Search (NAS) is an open and challenging problem in
m...
Knowing the similarity between sets of data has a number of positive
imp...
Multi-messenger astrophysics is a fast-growing, interdisciplinary field ...
Target encoding is an effective technique to deliver better performance ...
This report provides an overview of recent work that harnesses the Big D...
GPUs have limited memory and it is difficult to train wide and/or deep m...
Deep neural networks (DNNs) have achieved significant success in a varie...
Deep neural networks (DNNs) have achieved significant success in a varie...
As deep neural networks become more complex and input datasets grow larg...
Convolution is a critical component in modern deep neural networks, thus...