arXiv subjects

Sarthak Giri

Publications and source records attributed to Sarthak Giri.

6 recordsLinked to original sources

arXiv2026

Exploiting Speech LLM Representations for Multilingual and Cross-Lingual Parkinson's Disease Detection

Speech Large Language Models (Speech LLMs) have shown strong performance across diverse tasks, yet their utility for pathological speech analysis remains underexplored. In this work, we investigate the effectiveness of internal representations from encoder and decoder components of Speech LLMs for Parkinson's Disease (PD) detection across multilingual and cross-lingual settings. Our findings reveal that encoder representations consistently outperform their decoder counterparts in most models and settings and that pathological cues may be progressively attenuated as audio representations are projected into the language model space. We further show that generative outputs are less reliable for clinical tasks compared to internal representations. To leverage information spread across multiple layers, we propose a Squeeze-and-Excitation (SE)-based dynamic layer aggregation framework, which surpasses best-layer selection in multiple experiments, suggesting that PD-relevant acoustic cues are distributed across transformer layers rather than concentrated in one.

cs.SD↗

arXiv2025

Lived Experience in Dialogue: Co-designing Personalization in Large Language Models to Support Youth Mental Well-being

Youth increasingly turn to large language models (LLMs) for mental well-being support, yet current personalization in LLMs can overlook the heterogeneous lived experiences shaping their needs. We conducted a participatory study with youth, parents, and youth care workers (N=38), using co-created youth personas as scaffolds, to elicit community perspectives on how LLMs can facilitate more meaningful personalization to support youth mental well-being. Analysis identified three themes: person-centered contextualization responsive to momentary needs, explicit boundaries around scope and offline referral, and dialogic scaffolding for reflection and autonomy. We mapped these themes to persuasive design features for task suggestions, social facilitation, and system trustworthiness, and created corresponding dialogue extracts to guide LLM fine-tuning. Our findings demonstrate how lived experience can be operationalized to inform design features in LLMs, which can enhance the alignment of LLM-based interventions with the realities of youth and their communities, contributing to more effectively personalized digital well-being tools.

cs.HC↗

arXiv2025

Low redshift observational constraints on dark energy models using ANN - CosmicANNEstimator

We present CosmicANNEstimator (Cosmological Parameters Artificial Neural Network Estimator), a machine learning approach for constraining cosmological parameters within the Lambda Cold Dark Matter ($Λ$CDM) framework. Our methodology employs two specialized artificial neural networks (ANNs) designed to analyze Hubble parameter and Supernova data independently. The estimator is trained on synthetic data covering broad parameter ranges, with Gaussian random noise incorporated to simulate observational uncertainties. Our results demonstrate parameter estimates and associated uncertainties comparable to traditional Markov Chain Monte Carlo (MCMC) methods, establishing machine learning as an efficient alternative for cosmological parameter estimation. This work underscores the potential of neural network-based inference to complement traditional Bayesian methods and accelerate future cosmological analyses.

astro-ph.CO↗

arXiv2025

Gradient-based facial encoding for key generation to encrypt and decrypt multimedia data

Security systems relying on passwords are vulnerable to being forgotten, guessed, or breached. Likewise, biometric systems that operate independently are at risk of template spoofing and replay incidents. This paper introduces a biocryptosystem utilizing face recognition techniques to address these issues, allowing for the encryption and decryption of various file types through the Advanced Encryption Standard (AES). The proposed system creates a distinct 32-bit encryption key derived from facial features identified by Histogram of Oriented Gradients (HOG) and categorized using Support Vector Machines (SVM). HOG efficiently identifies edge-aligned facial features, even in dim lighting, ensuring that reliable biometric keys can be generated. This key is then used with AES to encrypt and decrypt a variety of data formats, such as text, audio, and video files. This encryption key, derived from an individual's distinctive facial traits, is exceedingly challenging for adversaries to reproduce or guess. The security and performance of the system have been validated through experiments using several metrics, including correlation analysis, Shannon entropy, normalized Hamming distance, and the avalanche effect on 25 different file types. Potential uses for the proposed system include secure file sharing, online transactions, and data archiving, making it a strong and trustworthy approach to safeguarding sensitive information by integrating the uniqueness of facial biometrics with the established security of AES encryption.

cs.CR↗

arXiv2024

Real-Time Scream Detection and Position Estimation for Worker Safety in Construction Sites

The construction industry faces high risks due to frequent accidents, often leaving workers in perilous situations where rapid response is critical. Traditional safety monitoring methods, including wearable sensors and GPS, often fail under obstructive or indoor conditions. This research introduces a novel real-time scream detection and localization system tailored for construction sites, especially in low-resource environments. Integrating Wav2Vec2 and Enhanced ConvNet models for accurate scream detection, coupled with the GCC-PHAT algorithm for robust time delay estimation under reverberant conditions, followed by a gradient descent-based approach to achieve precise position estimation in noisy environments. Our approach combines these concepts to achieve high detection accuracy and rapid localization, thereby minimizing false alarms and optimizing emergency response. Preliminary results demonstrate that the system not only accurately detects distress calls amidst construction noise but also reliably identifies the caller's location. This solution represents a substantial improvement in worker safety, with the potential for widespread application across high-risk occupational environments. The scripts used for training, evaluation of scream detection, position estimation, and integrated framework will be released at: https://github.com/Anmol2059/construction_safety.

cs.SD↗

arXiv2024

Analyzing Social Networks of Actors in Movies and TV Shows

The paper offers a comprehensive analysis of social networks among movie actors and directors in the film industry. Utilizing data from IMDb and Netflix, we leverage Python and NetworkX to uncover valuable insights into the movie industry's intricate web of collaborations. Key findings include identifying the top actors and directors in the OTT sector, tracking the rise of movies on OTT platforms, and analyzing centrality measures for actors. We also explore the hidden patterns within the movie data, unveiling the shortest paths between actors and predicting future collaborations. Cluster analysis categorizes movies based on various criteria, revealing the most insular and liberal clusters and identifying crossover actors bridging different segments of the industry. The study highlights that actors predominantly collaborate within language groups, transcending national boundaries. We investigate the degree of isolation of Bollywood from global cinema and identify actors working across world clusters. The project provides valuable insights into the evolving dynamics of the film industry and the impact of OTT platforms, benefiting industry professionals, scholars, and enthusiasts.

cs.SI↗