I’m interested in how AI systems use evidence, how their results should be evaluated, and how people interact with them. My work explores evidence-grounded language systems, multilingual speech and code-switching, and accessible interfaces. EEG classification provides another setting for studying reliable, subject-independent evaluation.
Multilingual speech processing under code-switching and background noise.
My contribution I developed the hybrid speech-processing pipeline and integrated noise suppression and 8-bit quantization.
At 10 dB SNR, WER fell from 31.45% to 9.20% with DeepFilterNet (Table III).
Evidence-grounded question answering over pharmaceutical regulatory documents.
My contribution I built PharmChunk and the verified hybrid RAG system, and constructed the PharmaEval v2 evaluation.
Held-out descriptive evaluation: faithfulness 0.960 on 25 questions.
A voice-controlled visual-assistance prototype for blind and low-vision users.
My contribution I led the team and integrated the camera/voice interface, cloud analysis and narration-coordinated capture.
Placed fourth among 1,800+ teams at the NextGen AI 2026 National Hackathon, held in collaboration with Google Gemini.
A four-stream temporal CNN for classifying rest and imagined movements in previously unseen participants.
My contribution I developed the four-stream CNN and implemented nested, participant-disjoint evaluation and reproducibility materials.
A 19.94M-parameter variant achieved 70.23% mean accuracy and 59.68% macro-F1 with 76% fewer parameters than the reference.
2026 2nd International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
Syed Javeed Pasha and Gaddam Ronit Reddy. “LinguaSense: A Multilingual Detection and Processing System for Seamless Language Identification and Adaptation.” 2026 2nd International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG), 2026. doi:10.1109/ICSTSDG69220.2026.11708060.
IC-AIMLC 2026
Submitted to Biomedical Signal Processing and Control.
Contribution to AI-Powered Developments in Medical Robotics: Data-Driven Techniques for Enhanced Surgical Efficiency.
Elsevier · Book published 31 July 2026
Presented at the First International Conference on Emerging Horizons in Mathematics and Computation, associated with Woxsen University and INTI International University, Malaysia.