Few-shot keyword spotting (FS-KWS) models usually require large-scale
an...
Streaming automatic speech recognition (ASR) models are restricted from
...
This paper proposes a novel, efficient transfer learning method, called
...
Transformer language models such as GPT-2 are difficult to quantize beca...
This technical report describes the details of our TASK1A submission of ...
Keyword spotting (KWS) plays an essential role in enabling speech-based ...
Keyword spotting is the task of detecting a keyword in streaming audio.
...
While using two-dimensional convolutional neural networks (2D-CNNs) in i...
In recent visual self-supervision works, an imitated classification
obje...
It is a practical research topic how to deal with multi-device audio inp...
While hand pose estimation is a critical component of most interactive
e...
Multi-task learning (MTL), which aims to improve performance by learning...
As edge devices become prevalent, deploying Deep Neural Networks (DNN) o...
Keyword spotting is an important research field because it plays a key r...
Convolutional Neural Networks are widely used in various machine learnin...
Nowadays, as edge devices such as smartphones become prevalent, there ar...
Convolutional Neural Networks are widely used to process spatial scenes,...
Recent advances in image-to-image translation have led to some ways to
g...
We tackle the blackbox issue of deep neural networks in the settings of
...
While convolutional neural networks (CNNs) are widely used for handling
...
This paper proposes a novel deep reinforcement learning (RL) method
inte...