Abstract

The evacuation path from inside a building to safe point outside becomes highly unpredictable due to changes in the local geometry or presence of obstacles during a disaster like a fire. During emergencies, Evacuees need appropriate information and hence prediction of an unobstructed path, as it emerges, needs to be computed well. Understanding the exits with its allowable people flow rate; the type - door or alternative exit such as windows, balconies, etc.; and its role as a node in the graph network is important to ensure safe and timely evacuation from a building. The study here evaluates how obstacles present in the evacuation route affect the removal of the last person. These obstacles, such as furniture, decrease the flow rate at which evacuees can escape. A subspace model is proposed for geometric spaces or carpet areas containing obstacles and is used to compute the shortest obstacle-free paths. The occupancy is considered within the subspaces containing obstacles. The proposed method clearly shows that a graphbased path generation using a subspace model improves the computation time, can be dynamically adapted, and can be scalable across geometric spaces. The results clearly show the impact of the obstacles, with a 2x to 6x rise when compared to obstacle-free scenarios.

Abstract

Social media provides a supportive and anonymous environment for discussing mental health issues, including depression. Existing research on identifying the cause of depression focuses primarily on improving classifier models, while neglecting the importance of learning better data representations. To address this gap, we introduce an architecture that enhances the identification of the cause of depression by learning improved data representations. Our work enables a deeper interpretation of the cause of depression in social media contexts, emphasizing the significance of effective rep- resentation learning for this task. Our work can act as a foundation for self-help applications in the field of mental health.

Abstract

This paper introduces a novel method for determining the best room to place an object in, for embodied scene rearrangement. While state-of-the-art approaches rely on large language models (LLMs) or reinforcement learned (RL) policies for this task, our approach, CLIPGraphs, efficiently combines commonsense domain knowledge, data-driven methods, and recent advances in multimodal learning. Specifically, it (a) encodes a knowledge graph of prior human preferences about the room location of different objects in home environments, (b) incorporates vision-language features to support multimodal queries based on images or text, and (c) uses a graph network to learn object-room affinities based on embeddings of the prior knowledge and the vision-language features. We demonstrate that our approach provides better estimates of the most appropriate location of objects from a benchmark set of object categories in comparison with state-of-the-art baselines

Abstract

Significant progress has been made in speaker-dependent Lip-to-Speech synthesis, which aims to generate speech from silent videos of talking faces. Current state-of-the-art approaches primarily employ non-autoregressive sequence-to-sequence architectures to directly predict mel-spectrograms or audio waveforms from lip representations. We hypothesize that the direct mel-prediction hampers training/model efficiency due to the entanglement of speech content with ambient information and speaker characteristics. To this end, we propose RobustL2S, a modularized framework for Lip-to-Speech synthesis. First, a non-autoregressive sequence-to-sequence model maps self-supervised visual features to a representation of disentangled speech content. A vocoder then converts the speech features into raw waveforms. Extensive evaluations confirm the effectiveness of our setup, achieving state-of-the-art performance on the unconstrained Lip2Wav dataset and the constrained GRID and TCD-TIMIT datasets. Speech samples from RobustL2S can be found at https://neha-sherin.github.io/RobustL2S/

Abstract

Fluency is a crucial goal of all Natural Language Generation (NLG) systems. Widely used automatic evaluation metrics fall short in capturing the fluency of machine-generated text. Assessing the fluency of NLG systems poses a challenge since these models are not limited to simply reusing words from the input but may also generate abstractions. Existing reference-based fluency evaluations, such as word overlap measures, often exhibit weak correlations with human judgments. This paper adapts an existing unsupervised technique for measuring text fluency without the need for any reference. Our approach leverages various word embeddings and trains language models using Recurrent Neural Network (RNN) architectures. We also experiment with other available multilingual Language Models (LMs). To assess the performance of the models, we conduct a comparative analysis across 10 Indic languages, correlating the obtained fluency scores with human judgments.

Abstract

Voice activity detection (VAD), is a signal processing technique used to determine whether a given speech signal contains voiced or unvoiced segments. VAD is used in various applications such as Speech Coding, Voice Controlled Systems, speech feature extraction, etc. For example, in Adaptive multirate (AMR) speech coding, VAD is used as an efficient way of coding different speech frames at different bit rates. In this paper, we implemented the application of a Zero-Phase Zero Frequency Resonator (ZP-ZFR) as VAD on hardware. ZP-ZFR is an Infinite Impulse Response (IIR) filter that offers the advantage of requiring a lower filter order, making it suitable for hardware implementation. The proposed system is implemented on the TIMIT database using the Nexys Video Artix-7 FPGA board. The hardware design is carried out using Vivado 2021.1, a popular tool for FPGA development. The Hardware Description Language (HDL) used for implementation is Verilog. The proposed system achieves good performance with low complexity. Therefore this work is implemented on hardware, which can be used in various applications. Index Terms—Voice Activity Detection (VAD), Zero-Phase Zero Frequency Resonator (ZP-ZFR), Zero Frequency Filter (ZFF), MATLAB, Field Programmable Gate Array (FPGA).

Abstract

Large language models (LLMs) and generative AI have emerged as the most important areas in the field of natural language processing (NLP). LLMs are considered to be a key component in several NLP tasks, such as summarization, question-answering, sentiment classification, and translation. Newer LLMs, such as Chat- GPT, BLOOMZ, and several such variants, are known to train on multilingual training data and hence are expected to process and generate text in multiple languages. Considering the widespread use of LLMs, evaluating their efficacy in multilingual settings is imperative. In this work, we evaluate the newest generative models (ChatGPT, mT0, and BLOOMZ) in the context of Indic languages. Specifically, we consider natural language generation (NLG) applications such as summarization and questionanswering in monolingual and cross-lingual settings. We observe that current generative models have limited capability for generating text in Indic languages in a zero-shot setting. In contrast, generative models perform consistently better on manual quality-based evaluation in Indic languages and English language generation. Considering limited generation performance, we argue that these LLMs are not intended to use in zero-shot fashion in downstream applications.

Abstract

Students need to understand the assessment of requirements correctness while building software systems. It helps produce products that meet the stakeholder objectives. This poster illustrates an experiment conducted as a tool-based collaborative assignment for assessing the correctness of software products using a Virtual Reality (VR) application as part of a CS300-level course at our University.

Abstract

Direct lighting from many area light sources is challenging due to variance from both choosing an important light and then a point on it. Resampled Importance Sampling (RIS) achieves low variance in such situations. However, it is limited to simple sampling strategies for its candidates. Specifically for area lights, we can improve the convergence of RIS by incorporating a better sampling strategy: Projected Solid Angle Sampling (ProjLTC). Naively combining RIS and ProjLTC improves equal sample convergence. However, it achieves little to no gain in equal time. We identify the core issue for the high run times and reformulate RIS for better integration with ProjLTC. Our method achieves better convergence and results in both equal sample and equal time. We evaluate our method on challenging scenes with varying numbers of area light sources and compare it to uniform sampling, RIS, and ProjLTC. In all cases, our method seldom performs worse than RIS and often performs better

Abstract

Language learning involves the correct acquisition of grammar skills. To facilitate learning with computer-assisted systems, automatic spoken grammatical error detection (SGED) is necessary. This work explores Automatic Speech Recognition (ASR), which decodes text from speech, for SGED. With current advancements in ASR technology, often it can be believed that these systems could capture spoken grammatical errors in the decoded text. However, these systems have an inherent bias from the language model towards the grammatically correct text. We explore the ASR-decoded text from commercially available current state-of-the-art systems considering a text-based GED algorithm and also its word-level confidence score (CS) for SGED. We perform the experiments on the spoken English data collected in-house from 13 subjects speaking 4110 grammatically erroneous and correct sentences. We found the highest relative improvement in SGED with CS is 15.36% compared to that with decoded text plus GED.