Abstract

Speech systems are sensitive to accent variations. This is a challenge in India, which has numerous languages but few linguistic studies on pronunciation variation. The growing number of L2 English speakers reinforces the need to study accents and L1-L2 interactions. We investigate Indian English (IE) accents and report our observations on regional and shared features. Specifically, we observe phonemic variations and phonotactics in speakers’ native languages and apply this to their English pronunciations. We demonstrate the influence of 18 Indian languages on IE by comparing native language features with IE pronunciations obtained from literature studies and phonetically annotated speech. Hence, we validate Indian language influences on IE by justifying pronunciation rules from the perspective of Indian language phonology. We obtain a comprehensive description of generalised and region-specific IE characteristics, which facilitates accent adaptation of existing speech systems.

Abstract

Cocaine use disorder (CUD) is described as a compulsive urge to seek and consume cocaine despite the inimical consequences. MRI studies from different modalities have shown that CUD patients exhibit structural and/or functional connectivity pathology among several brain regions. Nevertheless, both connectivities are commonly studied and analyzed separately, which may potentially obscure its relationship between them, and with the clinical pathology. Here, we compare and contrast structural and functional brain networks in CUD patients and healthy controls (HC) using multimodal fusion. The sample consisted of 63 (8 females) CUD patients and 42 (9 females) healthy controls (HC), recruited as part of the SUDMEX CONN database. For this, we computed a battery of graph-based measures from multi-shell diffusion-weighted imaging and resting state fc-fMRI to quantify local and global connectivity. Then we used multimodal canonical component analysis plus joint independent component analysis (mCCA+jICA) to compare between techniques, and evaluate group differences and its association with clinical alteration. Unimodal results showed a striatal decrease in the participation coefficient, but applied supervised data fusion revealed other regions with cocaine-related alterations in joint functional communication. When performing multimodal fusion analysis, we observed a higher centrality of the interrelationship and a lower participation coefficient in patients with CUD. In contrast to the unimodal approach, the multimodal fusion method was able to reveal latent information about brain regions involved in impairment due to cocaine abuse. The present results could help in understanding the pathology of CUD in order to develop better pre-treatment/post-treatment intervention designs

Abstract

Embodiments herein provide a system and method for automatically generating a sign language video from an input speech using the machine learning model. The method includes (i) extracting a plurality of spectrograms of an input speech by (a) encoding, using an encoder, a time domain series of the input speech to a frequency domain series, and (b) decoding, using a decoder, a plurality of tokens for time steps of the frequency domain series, (ii) generating a plurality of pose sequences for a current time step of the plurality of spectrograms using a first machine learning model, and (iii) automatically generating, using a discriminator of a second machine learning model, a sign language video for the input speech using the plurality of pose sequences and the plurality of spectrograms when the plurality of pose sequences are matched with corresponding the plurality of spectrograms that are extracted.

Abstract

The advances in Artificial Intelligence are creating new opportunities to improve people’s lives around the world, from business to healthcare, from lifestyle to education. For example, some systems profile the users using their demographic and behavioral characteristics to make certain domain-specific predictions. Often, such predictions impact the user’s life directly or indirectly (e.g., loan disbursement, determining insurance coverage, shortlisting applications, etc.). As a result, the concerns over such AI-enabled systems are also increasing. To address these concerns, such systems are mandated to be responsible: transparent, fair, and explainable to developers and end-users. In this paper, we present ComplAI, a unique framework to enable, observe, analyze and quantify explainability, robustness, performance, fairness, and model’s behavior in drift scenarios, and to provide a single Trust Factor that evaluates different supervised Machine Learning models not just from their ability to make correct predictions but from overall responsibility perspective. The framework helps users to (a) connect their models and enable explanations, (b) assess and visualize different aspects of the model such as robustness, drift susceptibility, and fairness, and (c) compare different models (from different model families or obtained through different hyperparameter settings) from an overall perspective thereby facilitating actionable recourse for improvement of the models. ComplAI is model agnostic and works with different supervised machine learning scenarios (i.e., Binary Classification, Multi-class Classification, and Regression) and frameworks (viz. scikit-learn, TensorFlow, etc.). It can be seamlessly integrated with any ML life-cycle framework. Thus, this already deployed framework aims to unify critical aspects of Responsible AI systems for regulating the development process of such real systems. The poster paper of ComplAI is also available

Abstract

Developing methods for extracting relevant legal information to aid legal practitioners is an active research area. In this regard, research efforts are being made by leveraging different kinds of information, such as meta-data, citations, keywords, sentences, paragraphs, etc. Similar to any text document, legal documents are composed of paragraphs. In this paper, we have analyzed the resourcefulness of paragraph-level information in capturing similarity among judgments for improving the performance of precedence retrieval. We found that the paragraph-level methods could capture the similarity among the judgments with only a few paragraph interactions and exhibit more discriminating power over the baseline document-level method. Moreover, the comparison results on two benchmark datasets for the precedence retrieval on the Indian supreme court judgments task show that the paragraph-level methods exhibit comparable performance with the state-of-the-art methods.

Abstract

This paper focuses on optimal beamforming to maximize the mean signal-to-noise ratio (SNR) for a passive reconfigurable intelligent surface (RIS)-aided multiple-input single-output (MISO) downlink system. We consider a realistic setting where both the direct and indirect (through RIS) links to the user equipment (UE) experience correlated Rician fading. Such a general fading model is particularly important to capture the impact of line-of-sight (LoS) and correlated multipath fading that may occur due to the compact placement of a large number of RIS elements. The assumption of passive RIS imposes the unit modulus constraint, which makes the beamforming problem non-convex. To tackle this issue, we apply semidefinite relaxation (SDR) to obtain the optimal phase-shift matrix and propose an iterative algorithm to obtain a statistically optimal solution for the transmit beamforming vector and RIS-phase shift matrix. Further, to measure the performance of the proposed beamforming scheme, we analyze key system performance metrics such as outage probability (OP) and ergodic capacity (EC). Similar to the existing works, the OP and EC evaluations rely on the numerical computation of the proposed iterative algorithm. However, this is not conducive to revealing the functional dependence of system performance on key parameters such as line-of-sight (LoS) components, correlated fading, number of reflecting elements, number of antennas at the base station (BS), and fading factor. To overcome this major limitation, we derive closed-form expressions for the optimal beamforming vector and phase shift matrix for various special cases of the above general fading model. These fixed-point solutions aid in deriving a closed-form solution for OP that further provides a direct evaluation of EC. These mathematical expressions are then used to gain useful insights into the system’s performance. We analytically establish the fact that correlated fading is more beneficial than the independent and identically distributed (i.i.d.) case when the LoS components are blocked. Further, we also analytically demonstrate that the maximum mean SNR improves linearly/quadratically with the number of RIS elements in the absence/presence of LoS component under i.i.d. fading.

Abstract

Brain stroke has become a significant burden on global health and thus we need remedies and prevention strategies to overcome this challenge. For this, the immediate identification of stroke and risk stratification is the primary task for clinicians. To aid expert clinicians, automated segmentation models are crucial. In this work, we consider the publicly available dataset ATLAS v2.0 to benchmark various end-to-end supervised U-Net style models. Specifically, we have benchmarked models on both 2D and 3D brain images and evaluated them using standard metrics. We have achieved the highest Dice score of 0.583 on the 2D transformer-based model and 0.504 on the 3D residual U-Net respectively. We have conducted the Wilcoxon test for 3D models to correlate the relationship between predicted and actual stroke volume.

Abstract

No Results Found

Abstract

We study communication models for channels with erasures in which the erasure pattern can be controlled by an adversary with partial knowledge of the transmitted codeword. In particular, we design block codes for channels with binary inputs with an adversary who can erase a fraction p of the transmitted bits. We consider causal adversaries, who must choose to erase an input bit using knowledge of that bit and previously transmitted bits, and myopic adversaries, who can choose an erasure pattern based on observing the transmitted codeword through a binary erasure channel with random erasures. For both settings we design efficient (polynomial time) encoding and decoding algorithms that use randomization at the encoder only. Our constructions achieve capacity for the causal and "sufficiently myopic" models. For the "insufficiently myopic" adversary, the capacity is unknown, but existing converses show the capacity is zero for a range of parameters. For all parameters outside of that range, our construction achieves positive rates.

Abstract

AI is about learning algorithms and huge amounts of data and are drivers of economic growth -- what does this mean for the field of development studies? Can we re-orient to twin AI studies and development theory and practice to generate how development challenges are identified and researched? To do this a good grasp is needed of AI internal mechanisms and outcomes in addressing development issues -- this argument will be developed through a case study of the ADAS [Advanced Driver Assistance System] deployment in India. Over and above discussing the ADAS we bring an anthropological lens to understand the social context that surrounds the system. Focusing on bus drivers, we offer findings from a qualitative and ethnographic study of drivers in a collaborative effort to achieve road safety by deploying AI-driven technology and empowering stakeholders in the transport industry in India especially, bus drivers as critical actors in the city transport network.