Individuals with language disorders often face significant communication challenges due to their limited language processing and comprehension abilities, which also affect their interactions with voice-assisted systems that mostly rely on Automatic Speech Recognition (ASR). Despite advancements in ASR that address disfluencies, there has been little attention on integrating non-verbal communication methods, such as gestures, which individuals with language disorders substantially rely on to supplement their communication. Recognizing the need to interpret the latent meanings of visual information not captured by speech alone, we propose a gesture-aware ASR system utilizing a multimodal large language model with zero-shot learning for individuals with speech impairments. Our experiment results and analyses show that including gesture information significantly enhances semantic understanding. This study can help develop effective communication technologies, specifically designed to meet the unique needs of individuals with language impairments.

A pilot-scale thermal plasma gasification system (TPGS) for waste-to-energy (WTE) was experimentally investigated to evaluate NO x formation and mitigation during plasma operation using air and nitrogen. NO was the predominant species, mainly generated through the vibrationally enhanced Zeldovich mechanism under high specific energy input (SEI) conditions. NO x concentrations decreased from 2545 – 3363 ppm to 1043 – 1162 ppm for air plasma and from 4827 – 5009 ppm to 1676 – 2095 ppm for N 2 plasma downstream of the wet scrubber at an SEI of 684 – 1073 kJ/mol, with reduction efficiencies of 31% – 42% for NO and 75% – 81% for NO 2 . Long-term operation demonstrated stable performance and an acidification rate of the scrubbing solution equivalent to 2.9 neutralization cycles per day, requiring approximately 1.4 kg/day of NaOH. This experimental study shows the first results of pilot-scale TPGS under high SEI conditions and provides key parameters for effective NO x control in plasma-based WTE systems, in comparison with previous research at low SEI and laboratory scales. • A pilot-scale thermal plasma gasification system was demonstrated for NO x characterization. • NO formation was governed by the vibrationally enhanced Zeldovich mechanism under high SEI. • Wet scrubbing significantly reduced NO 2 and partially mitigated NO emissions (p < 0.05). • Experiments offer practical NO x control in plasma-based waste-to-energy systems.

The rapid development and prevalence of generative AI have made it easy for people to create high-quality deepfake images and videos, but their abuses have also increased exponentially. To mitigate potential social disruption, it is crucial to quickly detect the authenticity of each deepfake content hidden in a sea of information. While researchers have worked on developing deep learning-based methods, the deepfake datasets utilized in these studies are far from the real world in terms of their qualities; most popular deepfake datasets are human-distinguishable. To address this problem, we present a novel deepfake dataset, HiDF, a high-quality and human-indistinguishable deepfake dataset consisting of 62K images and 8K videos. HiDF is a meticulously curated dataset that includes diverse subjects that have undergone rigorous quality checks. A comparison of the quality between HiDF and existing deepfake datasets demonstrates that HiDF is human-indistinguishable. Hence, it can be a valuable benchmark dataset for deepfake detection tasks. Data and code (https://github.com/DSAIL-SKKU/HiDF) are publicly available for future deepfake detection research.