Related papers: SALAD: Self-Adaptive Link Adaptation

We propose three regularization-based speaker adaptation approaches to adapt the attention-based encoder-decoder (AED) model with very limited adaptation data from target speakers for end-to-end automatic speech recognition. The first…

Future 5G cellular networks supporting ultra-reliable, low-latency communications (URLLC) could employ random access communication to reduce the overhead compared to scheduled access techniques used in 4G networks. We consider a wireless…

Path planning and optimization for unmanned aerial vehicles (UAVs)-assisted next-generation wireless networks is critical for mobility management and ensuring UAV safety and ubiquitous connectivity, especially in dense urban environments…

Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains. To handle large-scale graphs, most of the existing…

Fully convolutional neural networks have made promising progress in joint liver and liver tumor segmentation. Instead of following the debates over 2D versus 3D networks (for example, pursuing the balance between large-scale 2D pretraining…

High-level synthesis (HLS) allows hardware designers to create hardware designs with high-level programming languages like C/C++/OpenCL, which greatly improves hardware design productivity. However, existing HLS flows require programmers'…

Spiking Neural Networks (SNNs) are promising for low-power computation due to their event-driven mechanism but often suffer from lower accuracy compared to Artificial Neural Networks (ANNs). ANN-to-SNN knowledge distillation can improve SNN…

Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In software engineering, LLM-powered coding agents have garnered…

Neural architecture search (NAS) has attracted much attention and has been explored for automatic speech recognition (ASR). In this work, we focus on streaming ASR scenarios and propose the latency-controlled NAS for acoustic modeling.…

Approximate Logic Synthesis (ALS) is the process of synthesizing and mapping a given Boolean network to a library of logic cells so that the magnitude/rate of error between outputs of the approximate and initial (exact) Boolean netlists is…

Artificial neural network training with stochastic gradient descent can be destabilized by "bad batches" with high losses. This is often problematic for training with small batch sizes, high order loss functions or unstably high learning…

We introduce NADA, the first framework to autonomously design network algorithms by leveraging the generative capabilities of large language models (LLMs). Starting with an existing algorithm implementation, NADA enables LLMs to create a…

Recently, the spatial modulation (SM) technique has been proposed for visible light communication (VLC). This paper investigates the average symbol error rate (SER) for the VLC using adaptive spatial modulation (ASM). In the system, the…

Accurate and stable feature matching is critical for computer vision tasks, particularly in applications such as Simultaneous Localization and Mapping (SLAM). While recent learning-based feature matching methods have demonstrated promising…

Self-supervised learning (SSL) leverages large amounts of unlabelled data to learn rich speech representations, fostering improvements in automatic speech recognition (ASR), even when only a small amount of labelled data is available for…

The long-range and low energy consumption requirements in Internet of Things (IoT) applications have led to a new wireless communication technology known as Low Power Wide Area Network (LPWANs). In recent years, the Long Range (LoRa)…

We consider the uplink of non-cooperative multi-cellular systems deploying multiple antenna elements at the base stations (BS), covering both the cases of conventional and very large number of antennas. Given the inevitable pilot…

Extended Reality (XR) is one of the most important media applications in 5\textsuperscript{th} Generation (5G) and 5G-Advanced. XR traffic is characterized by high data rates with bounded latency constraints, which is challenging for…

Fifth generation new radio aims to facilitate new use cases in wireless communications. Some of these new use cases have highly de-manding latency requirements; many of the powerful forward error correction codes deployed in current…

Label assignment is a crucial process in object detection, which significantly influences the detection performance by determining positive or negative samples during training process. However, existing label assignment strategies barely…