相关论文: The Statistical Model for Ticker, an Adaptive Sing…

Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual feature. Such a formulation does not treat each word of a query sentence on par when modeling language to…

For people with visual impairments, tactile graphics are an important means to learn and explore information. However, raised line tactile graphics created with traditional materials such as embossing are static. While available refreshable…

Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, fully end-to-end model that performs…

Multi-talker speech recognition and target-talker speech recognition, both involve transcription in multi-talker contexts, remain significant challenges. However, existing methods rarely attempt to simultaneously address both tasks. In this…

TypeShift is a tool for visualizing linguistic patterns in the timing of typing production. Language production is a complex process which draws on linguistic, cognitive and motor skills. By visualizing holistic trends in the typing…

Simulating Standardized Patients with cognitive impairment offers a scalable and ethical solution for clinical training. However, existing methods rely on discrete prompt engineering and fail to capture the heterogeneity of deficits across…

In today's world, time is a very important resource. In our busy lives, most of us hardly have time to read the complete news so what we have to do is just go through the headlines and satisfy ourselves with that. As a result, we might miss…

Even human intelligence system fails to offer 100% accuracy in identifying speeches from a specific individual. Machine intelligence is trying to mimic humans in speaker identification problems through various approaches to speech feature…

Access to non-verbal cues in social interactions is vital for people with visual impairment. It has been shown that non-verbal cues such as eye contact, number of people, their names and positions are helpful for individuals who are blind.…

Event cameras offer significant advantages over traditional frame-based sensors, including higher temporal resolution, lower latency and dynamic range. However, efficiently converting event streams into formats compatible with standard…

Incorporating item content information into click-through rate (CTR) prediction models remains a challenge, especially with the time and space constraints of industrial scenarios. The content-encoding paradigm, which integrates user and…

Goal-oriented semantic communication (SC) aims to revolutionize communication systems by transmitting only task-essential information. However, current approaches face challenges such as joint training at transceivers, leading to redundant…

Scoring systems are classification models that only require users to add, subtract and multiply a few meaningful numbers to make a prediction. These models are often used because they are practical and interpretable. In this paper, we…

Natural languages are believed to be (mildly) context-sensitive. Despite underpinning remarkably capable large language models, transformers are unable to model many context-free language tasks. In an attempt to address this limitation in…

Code-switching, the alternation of languages within a single discourse, presents a significant challenge for Automatic Speech Recognition. Despite the unique nature of the task, performance is commonly measured with established metrics such…

Usable speech criteria are proposed to extract minimally corrupted speech for speaker identification (SID) in co-channel speech. In co-channel speech, either speaker can randomly appear as the stronger speaker or the weaker one at a time.…

Understanding why certain individuals work well (or poorly) together as a team is a key research focus in the psychological and behavioral sciences and a fundamental problem for team-based organizations. Nevertheless, we have a limited…

This report introduces the Attention Visualizer package, which is crafted to visually illustrate the significance of individual words in encoder-only transformer-based models. In contrast to other methods that center on tokens and…

This study aims to explore efficient tuning methods for the screenshot captioning task. Recently, image captioning has seen significant advancements, but research in captioning tasks for mobile screens remains relatively scarce. Current…

The goal of our project is to develop an accurate tagger for questions posted on Stack Exchange. Our problem is an instance of the more general problem of developing accurate classifiers for large scale text datasets. We are tackling the…