Nabanita Das

Papers

Total Citations

H-Index

About

Nabanita Das is a researcher at the intersection of deep learning, bioacoustics, and speech processing, with a focus on leveraging artificial intelligence for ecological monitoring and signal analysis. Her most cited work introduces a deep transfer learning framework for the automated identification of bird songs, a critical tool for avian biodiversity conservation and ornithological research. By applying convolutional neural networks (CNNs) to vocalization data, Das demonstrates how advanced speech classification techniques can be repurposed to quantify bird presence, offering a scalable solution for environmental monitoring. This paper has garnered 3 citations, marking it as a foundational contribution to AI-driven ecology. In parallel, Das has contributed to the broader field of speech processing through a bibliometric and co-occurrence analysis of literature published between 2015 and mid-2021. This work maps the evolving landscape of voice identification, interactive voice systems, and emotion recognition, providing a valuable roadmap for researchers in signal processing. Her dual focus on applied deep learning for conservation and systematic literature analysis underscores her versatility and impact, making her a promising voice in both computational bioacoustics and speech technology.