arXiv subjects

Kawshik Kumar Paul

Publications and source records attributed to Kawshik Kumar Paul.

4 recordsLinked to original sources

arXiv2026

Building and Evaluating a Synthetic Bengali Speech Resource for Telecom Customer Care

Speech systems used in customer-facing applications often require domain-specific language coverage. We present a synthetic Bengali speech dataset for telecom customer-care scenarios. The dataset contains 10,000 audio-text pairs, approximately 26.82 hours of 24 kHz speech, and predefined train, validation, and test splits of 9,000, 500, and 500 examples. It is publicly released on Hugging Face under the CC-BY-4.0 license. The speech was generated with OmniVoice in voice-cloning mode using a real female reference recording and transcript, with bfloat16 precision, 16 diffusion sampling steps, and a speaking-rate control value of 1.0. Along with the original Bengali text, the dataset provides a normalized transcript field designed for ASR/STT training and evaluation. We report an automatic intelligibility check over all 10,000 samples using a domain-adapted Whisper ASR model fine-tuned from bengaliAI/tugstugi_bengaliai-regional-asr_whisper-medium, along with a manual listening check on selected samples. The evaluation gives an average WER of 2.54%, an average CER of 0.59%, and median WER and CER values of 0.00%. These results suggest strong text-audio consistency under the selected automatic evaluation pipeline, while the paper also discusses the limitations of synthetic speech and STT-based evaluation.

cs.CL↗

arXiv2025

A Low-Cost ATmega32-Based Embedded System for Automated Patient Queue and Health Data Management in Private Medical Chambers

This paper presents a low-cost, stand-alone embedded system that automates patient queue handling and basic health data acquisition for small private medical chambers. The proposed design separates interaction into two physically distinct modules: a patient's self-service corner for entering basic details and measuring vital signs, and a doctor's corner for reviewing the current patient's information and advancing the queue. A single ATmega32 microcontroller coordinates both modules, interfacing with an LM35 temperature sensor, an XD-58C pulse sensor, matrix keypads for data entry, and dual 16$\times$2 LCDs for guided interaction and clinician-side display. Unlike IoT-first approaches that require continuous connectivity and higher deployment overhead, the system operates offline and provides deterministic local operation suitable for resource-constrained settings. Experimental validation shows temperature readings within $\pm 1^{\circ}$C (LM35 range tested), resting pulse readings within $\pm 3$~BPM, and button-to-display latency below 1.2~s, demonstrating reliable real-time performance under limited hardware resources.

cs.HC↗

arXiv2025

An Architecture for Remote Container Builds and Artifact Delivery Using a Controller-Light Jenkins CI/CD Pipeline

Resource-intensive builds are often executed directly on the controller by conventional Jenkins installations, which can lower reliability and overload system resources. Jenkins functions as a containerized controller with persistent volumes in the controller-light CI/CD framework presented in this paper, delegating difficult build and packaging tasks to a remote Docker host. The controller container maintains secure SSH connections to remote compute nodes while focusing solely on orchestration and reporting. Atomic deployments with time-stamped backups, containerized build environments, immutable artifact packaging, and automated notifications are all included in the system. Faster build throughput, reduced CPU and RAM consumption on the controller, and reduced artifact delivery latency are all revealed by experimental evaluation. For small and medium-sized DevOps businesses looking for scalable automation without adding orchestration complexity, this method offers a repeatable, low-maintenance solution.

cs.SE↗

arXiv2025

A Patient-Centric Blockchain Framework for Secure Electronic Health Record Management: Decoupling Data Storage from Access Control

We present a patient-centric architecture for electronic health record (EHR) sharing that separates content storage from authorization and audit. Encrypted FHIR resources are stored off-chain; a public blockchain records only cryptographic commitments and patient-signed, time-bounded permissions using EIP-712. Keys are distributed via public-key wrapping, enabling storage providers to remain honest-but-curious without risking confidentiality. We formalize security goals (confidentiality, integrity, cryptographically attributable authorization, and auditability of authorization events) and provide a Solidity reference implementation deployed as single-patient contracts. On-chain costs for permission grants average 78,000 gas (L1), and end-to-end access latency for 1 MB records is 0.7--1.4s (mean values for S3 and IPFS respectively), dominated by storage retrieval. Layer-2 deployment reduces gas usage by 10--13x, though data availability charges dominate actual costs. We discuss metadata privacy, key registry requirements, and regulatory considerations (HIPAA/GDPR), demonstrating a practical route to restoring patient control while preserving security properties required for sensitive clinical data.

cs.CR↗