We propose a sign language translation system based on human keypoint estimation. It is well-known that many problems in the field of computer vision require a massive dataset to train deep neural network models. The situation is even worse when it comes to the sign language translation problem as it is far more difficult to collect high-quality training data. In this paper, we introduce the KETI (Korea Electronics Technology Institute) sign language dataset, which consists of 14,672 videos of high resolution and quality. Considering the fact that each country has a different and unique sign language, the KETI sign language dataset can be the starting point for further research on the Korean sign language translation. Using the KETI sign language dataset, we develop a neural network model for translating sign videos into natural language sentences by utilizing the human keypoints extracted from the face, hands, and body parts. The obtained human keypoint vector is normalized by the mean and standard deviation of the keypoints and used as input to our translation model based on the sequence-to-sequence architecture. As a result, we show that our approach is robust even when the size of the training data is not sufficient. Our translation model achieved 93.28% (55.28%, respectively) translation accuracy on the validation set (test set, respectively) for 105 sentences that can be used in emergency situations. We compared several types of our neural sign translation models based on different attention mechanisms in terms of classical metrics for measuring the translation performance.

Semantic image segmentation has a wide range of applications. When it comes to medical image segmentation, its accuracy is even more important than those of other areas because the performance gives useful information directly applicable to disease diagnosis, surgical planning, and history monitoring. The state-of-the-art models in medical image segmentation are variants of encoder-decoder architecture, which is called U-Net. To effectively reflect the spatial features in feature maps in encoder-decoder architecture, we propose a spatially adaptive weighting scheme for medical image segmentation. Specifically, the spatial feature is estimated from the feature maps, and the learned weighting parameters are obtained from the computed map, since segmentation results are predicted from the feature map through a convolutional layer. Especially in the proposed networks, the convolutional block for extracting the feature map is replaced with the widely used convolutional frameworks: VGG, ResNet, and Bottleneck Resent structures. In addition, a bilinear up-sampling method replaces the up-convolutional layer to increase the resolution of the feature map. For the performance evaluation of the proposed architecture, we used three data sets covering different medical imaging modalities. Experimental results show that the network with the proposed self-spatial adaptive weighting block based on the ResNet framework gave the highest IoU and DICE scores in the three tasks compared to other methods. In particular, the segmentation network combining the proposed self-spatially adaptive block and ResNet framework recorded the highest 3.01% and 2.89% improvements in IoU and DICE scores, respectively, in the Nerve data set. Therefore, we believe that the proposed scheme can be a useful tool for image segmentation tasks based on the encoder-decoder architecture.

This paper describes an audio source separation that is based on nonnegative matrix factorization (NMF) and expectation maximization (EM). For stable and high-performance separation, an effective auxiliary source separation that extracts source residuals and reprojects them onto proper sources is proposed by taking into account an ambiguous region among sources and a source's refinement. Specifically, an additional NMF (model) is designed for the ambiguous region — whose elements are not easily represented by any existing or predefined NMFs of the sources. The residual signal can be extracted by inserting the aforementioned model into the NMF-EM-based audio separation. Then, it is refined by the weighted parameters of the separation and reprojected onto the separated sources. Experimental results demonstrate that the proposed scheme (outlined above) is more stable and outperforms existing algorithms by, on average, 4.4 dB in terms of the source distortion ratio.

Recent advances in speech deepfake detection (SDD) have significantly improved artifacts-based detection in spoofed speech. However, most models overlook speech naturalness, a crucial cue for distinguishing bona fide speech from spoofed speech. This study proposes naturalness-aware curriculum learning, a novel training framework that leverages speech naturalness to enhance the robustness and generalization of SDD. This approach measures sample difficulty using both ground-truth labels and mean opinion scores, and adjusts the training schedule to progressively introduce more challenging samples. To further improve generalization, a dynamic temperature scaling method based on speech naturalness is incorporated into the training process. A 23% relative reduction in the EER was achieved in the experiments on the ASVspoof 2021 DF dataset, without modifying the model architecture. Ablation studies confirmed the effectiveness of naturalness-aware training strategies for SDD tasks.