The proposed BERT-based rescoring approach gives a significant improvement of the word error rate (WER) over the ASR system without rescoring semantic models under all experimented conditions and with n-gram and recurrent NN language model (Long Short-Term model, LSTM)....
Deep Neural Network (DNN) models are widely used for image classification. While they offer high performance in terms of accuracy, researchers are concerned about if these models inappropriately make inferences using features irrelevant to the target object in a given image. To address this concern,...
We implement basic layers for CNN models. You can use these layers to build your own model and customize how to deployment your model. You can put some layers into SGX and the rest of the model to GPU. You can refer to teeslice/sgx_resnet_cifar.py and teeslice/sgx_resnet_cifar_tee...
To detect software vulnerabilities with better performance, deep neural networks (DNNs) have received extensive attention recently. However, these vulnerability detection DNN models trained with code representations are vulnerable to specific perturbations on code representations. This motivates us to rethink ...
Our results show that dCoNNear not only accurately simulates all processing stages of existing non-DNN biophysical models but also eliminates audible artifacts, thereby enhancing the sound quality of the resulting hearing aid algorithms. This study presents a novel, artifact-free closed-loop framework...
Notably, on CIFAR-100, with 2.3X and 2.4X compression ratios, our models have 1.96% and 2.21% higher top-1 accuracy than the original ResNet-20 and ResNet-32, respectively. For compressing ResNet-18 on ImageNet, our model achieves 2.47X FLOPs reduction without accuracy loss. 展开 ...
Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from mon... S Tong,PN Garner,H Bourlard - 《Speech Communication》 被...
Our results show that dCoNNear not only accurately simulates all processing stages of existing non-DNN biophysical models but also eliminates audible artifacts, thereby enhancing the sound quality of the resulting hearing aid algorithms. This study presents a novel, artifact-free closed-loop framework...
感觉可能更靠谱一些，结果更具有解释性和普适性针对neuMF，包括何老师的实现与Tensorflow-models的实现...
We then use the dataset to train a set of deep neural network models suited to mobile and constrained deployment scenarios to determine the extent to which it may be possible to efficiently and accurately classify these `rainy' conditions. The most lightweight of these models (MobileNetV3 small...