Related papers: FCPE: A Fast Context-based Pitch Estimation Model

Rich textual and topological information of textual graphs need to be modeled in real-world applications such as webpages, e-commerce, and academic articles. Practitioners have been long following the path of adopting a shallow text encoder…

The reconstruction of clipped speech signals is an important task in audio signal processing to achieve an enhanced audio quality for further processing. In this paper, Frequency Selective Extrapolation (FSE), which is commonly used for…

Foreign accent conversion (FAC) in speech processing remains a challenging task. Building on the remarkable success of large language models (LLMs) in Text-to-Speech (TTS) tasks, this study investigates the adaptation of LLM-based…

Large Language Models (LLMs) have demonstrated impressive performance across various tasks, and their application in edge scenarios has attracted significant attention. However, sparse-activated Mixture-of-Experts (MoE) models, which are…

The Mixture-of-Experts (MoE) architecture has emerged as a promising approach to mitigate the rising computational costs of large language models (LLMs) by selectively activating parameters. However, its high memory requirements and…

Fast Fourier convolution (FFC) is the recently proposed neural operator showing promising performance in several computer vision problems. The FFC operator allows employing large receptive field operations within early layers of the neural…

Real-time semantic segmentation is playing a more important role in computer vision, due to the growing demand for mobile devices and autonomous driving. Therefore, it is very important to achieve a good trade-off among performance, model…

This paper considers pilot-based channel estimation in large-scale multiple-input multiple-output (MIMO) communication systems, also known as massive MIMO, where there are hundreds of antennas at one side of the link. Motivated by the fact…

Monocular depth estimation is an important task that can be applied to many robotic applications. Existing methods focus on improving depth estimation accuracy via training increasingly deeper and wider networks, however these suffer from…

Few-Shot Class Incremental Learning (FSCIL) is a challenging continual learning task, where limited training examples are available during several learning sessions. To succeed in this task, it is necessary to avoid over-fitting new classes…

Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets. State-of-the-art methods are, however, not directly transferable to real-time applications or embedded devices, since…

Real-time semantic segmentation is desirable in many robotic applications with limited computation resources. One challenge of semantic segmentation is to deal with the object scale variations and leverage the context. How to perform…

With the recent growth of remote work, online meetings often encounter challenging audio contexts such as background noise, music, and echo. Accurate real-time detection of music events can help to improve the user experience. In this…

In the domain of question-answering in NLP, the retrieval of Frequently Asked Questions (FAQ) is an important sub-area which is well researched and has been worked upon for many languages. Here, in response to a user query, a retrieval…

Magnetoencephalography (MEG) and Electroencephalography (EEG) source estimates have thus far mostly been derived sample by sample, i.e., independent of each other in time. However, neuronal assemblies are heavily interconnected,…

Due to the diversity of scene text in aspects such as font, color, shape, and size, accurately and efficiently detecting text is still a formidable challenge. Among the various detection approaches, segmentation-based approaches have…

Serving Large Language Models (LLMs) in production faces significant challenges from highly variable request patterns and severe resource fragmentation in serverless clusters. Current systems rely on static pipeline configurations that…

Because of the availability of larger datasets and recent improvements in the generative model, more realistic Deepfake videos are being produced each day. People consume around one billion hours of video on social media platforms every…

Foundation models (FMs) have recently shown remarkable in-context learning (ICL) capabilities across diverse scientific domains. In this work, we introduce a unified in-context learning foundation model (ICL-FM) framework for materials…

The popular VQ-VAE models reconstruct images through learning a discrete codebook but suffer from a significant issue in the rapid quality degradation of image reconstruction as the compression rate rises. One major reason is that a higher…