Related papers: CAST: Channel-Aware Spatial Transfer Learning with…
In this study, we present synchronous bilingual Connectionist Temporal Classification (CTC), an innovative framework that leverages dual CTC to bridge the gaps of both modality and language in the speech translation (ST) task. Utilizing…
In this study, a novel transmission scheme is proposed to serve radar-sensing and communication objectives at the same time and allocated bandwidth. The proposed transmitted frame non-orthogonally superimposes two different waveforms, which…
The ability to generate natural language explanations conditioned on the visual perception is a crucial step towards autonomous agents which can explain themselves and communicate with humans. While the research efforts in image and video…
Arbitrary style transfer (AST) transfers arbitrary artistic styles onto content images. Despite the recent rapid progress, existing AST methods are either incapable or too slow to run at ultra-resolutions (e.g., 4K) with limited resources,…
Although great progresses have been made in automatic speech recognition (ASR), significant performance degradation is still observed when recognizing multi-talker mixed speech. In this paper, we propose and evaluate several architectures…
We introduce the Convolutional Set Transformer (CST), a novel neural architecture designed to process image sets of arbitrary cardinality that are visually heterogeneous yet share high-level semantics - such as a common category, scene, or…
Radar detection and communication can be operated simultaneously in joint radar-communication (JRC) system. In this paper, we propose a bistatic JRC system which is applicable in multi-path environments. Basing on a novel joint waveform, a…
Humans are adept at leveraging visual cues from lip movements for recognizing speech in adverse listening conditions. Audio-Visual Speech Recognition (AVSR) models follow similar approach to achieve robust speech recognition in noisy…
In IoT based distributed network of cameras, real-time multi-camera video analytics is challenged by high bandwidth demands and redundant visual data, creating a fundamental tension where reducing data saves network overhead but can degrade…
Developing comprehensive assistive technologies requires the seamless integration of visual and auditory perception. This research evaluates the feasibility of a modular architecture inspired by core functionalities of perceptive systems…
Triggered by the success of transformers in various visual tasks, the spatial self-attention mechanism has recently attracted more and more attention in the computer vision community. However, we empirically found that a typical vision…
Sign language is the primary language for people with a hearing loss. Sign language recognition (SLR) is the automatic recognition of sign language, which represents a challenging problem for computers, though some progress has been made…
In recent years, deep learning techniques have been used to develop sign language recognition systems, potentially serving as a communication tool for millions of hearing-impaired individuals worldwide. However, there are inherent…
Embodied perception is essential for intelligent vehicles and robots in interactive environmental understanding. However, these advancements primarily focus on vision, with limited attention given to using 3D modeling sensors, restricting a…
Place recognition is a key module in robotic navigation. The existing line of studies mostly focuses on visual place recognition to recognize previously visited places solely based on their appearance. In this paper, we address structural…
Sign language recognition is crucial for individuals with hearing impairments to break communication barriers. However, previous approaches have had to choose between efficiency and accuracy. Such as RNNs, LSTMs, and GCNs, had problems with…
Zero-shot learning (ZSL) enables the recognition of novel classes by leveraging semantic knowledge transfer from known to unknown categories. This knowledge, typically encapsulated in attribute descriptions, aids in identifying…
Synthetic aperture radar (SAR) image change detection is a critical task and has received increasing attentions in the remote sensing community. However, existing SAR change detection methods are mainly based on convolutional neural…
This paper presents the Speech Technology Center (STC) speaker recognition (SR) systems submitted to the VOiCES From a Distance challenge 2019. The challenge's SR task is focused on the problem of speaker recognition in single channel…
A promising approach for steering auditory attention in complex listening environments relies on Auditory Attention Decoding (AAD), which aim to identify the attended speech stream in a multiple speaker scenario from neural recordings.…