Rajesh Sharma


2024

pdf bib
Revisiting the Classics: A Study on Identifying and Rectifying Gender Stereotypes in Rhymes and Poems
Aditya Narayan Sankaran | Vigneshwaran Shankaran | Sampath Lonka | Rajesh Sharma
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Rhymes and poems are a powerful medium for transmitting cultural norms and societal roles. However, the pervasive existence of gender stereotypes in these works perpetuates biased perceptions and limits the scope of individuals’ identities. Past works have shown that stereotyping and prejudice emerge in early childhood, and developmental research on causal mechanisms is critical for understanding and controlling stereotyping and prejudice. This work contributes by gathering a dataset of rhymes and poems to identify gender stereotypes and propose a model with 97% accuracy to identify gender bias. Gender stereotypes were rectified using a Large Language Model (LLM) and its effectiveness was evaluated in a comparative survey against human educator rectifications. To summarize, this work highlights the pervasive nature of gender stereotypes in literary works and reveal the potential of LLMs to rectify gender stereotypes. This study raises awareness and promotes inclusivity within artistic expressions, making a significant contribution to the discourse on gender equality.

pdf bib
Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake
Orchid Chetia Phukan | Gautam Kashyap | Arun Balaji Buduru | Rajesh Sharma
Findings of the Association for Computational Linguistics: NAACL 2024

In this work, we investigate multilingual speech Pre-Trained models (PTMs) for Audio deepfake detection (ADD). We hypothesize thatmultilingual PTMs trained on large-scale diverse multilingual data gain knowledge about diverse pitches, accents, and tones, during theirpre-training phase and making them more robust to variations. As a result, they will be more effective for detecting audio deepfakes. To validate our hypothesis, we extract representations from state-of-the-art (SOTA) PTMs including monolingual, multilingual as well as PTMs trained for speaker and emotion recognition, and evaluated them on ASVSpoof 2019 (ASV), In-the-Wild (ITW), and DECRO benchmark databases. We show that representations from multilingual PTMs, with simple downstream networks, attain the best performance for ADD compared to other PTM representations, which validates our hypothesis. We also explore the possibility of fusion of selected PTM representations for further improvements in ADD, and we propose a framework, MiO (Merge into One) for this purpose. With MiO, we achieve SOTA performance on ASV and ITW and comparable performance on DECRO with current SOTA works.