Although Deep neural networks (DNNs) have shown a strong capacity to sol...
Transducer is one of the mainstream frameworks for streaming speech
reco...
Inference time, model size, and accuracy are critical for deploying deep...
Model quantization enables the deployment of deep neural networks under
...
Most existing pruning works are resource-intensive, requiring retraining...
Most of the existing works use projection functions for ternary quantiza...
Although Deep Neural Networks (DNNs) have shown a strong capacity to sol...
Magnetic resonance images play an essential role in clinical diagnosis b...
Matrix Factorization (MF) is one of the most successful Collaborative
Fi...
With the development of online business, customer service agents gradual...
We introduce the well-established social scientific concept of social
so...
We propose pruning ternary quantization (PTQ), a simple, yet effective,
...
This paper describes USTC-NELSLIP's submissions to the IWSLT2021 Simulta...
Task-oriented conversational modeling with unstructured knowledge access...
Edge learning (EL), which uses edge computing as a platform to execute
m...
The lack of interpretability of existing CNN-based hand detection method...
Large-scale shape-changing interfaces have great potential, but creating...
While the security of the cloud remains a concern, a common practice is ...
Existing hand detection methods usually follow the pipeline of multiple
...
Recent years has witnessed dramatic progress of neural machine translati...
This paper describes the USTC-NEL system to the speech translation task ...
Recurrent Neural Networks with Long Short-Term Memory cell (LSTM-RNN) ha...
This paper describes the USTC_NELSLIP systems submitted to the Trilingua...