Year-2025Year-2025http://repository.iiitd.edu.in/xmlui/handle/123456789/18062026-08-24T13:04:32Z2026-08-24T13:04:32ZTowards better knowledge distillation with multi-teacher for efficient audio deepfake detectionDua, ChaitanyaSachdeva, HimanshuBuduru, Arun Balaji (Advisor)http://repository.iiitd.edu.in/xmlui/handle/123456789/20022026-08-21T22:00:31Z2025-11-27T00:00:00ZTowards better knowledge distillation with multi-teacher for efficient audio deepfake detection
Dua, Chaitanya; Sachdeva, Himanshu; Buduru, Arun Balaji (Advisor)
This project focuses on the development and evaluation of a student model for audio deepfake detection, leveraging a single teacher model from a selection of advanced architectures, including XLSR, Facebook MMS, X-vector, UniSpeech, and Wav2Vec2. The primary objective is to enhance the detection capabilities of spoofed audio by utilizing the rich feature representations learned by these teacher models. The training process involves transferring knowledge from the teacher model to the student model, which is designed to classify audio samples as either genuine or spoofed. This approach capitalizes on the strengths of the selected teacher model, enabling the student model to learn ef fective discriminative features while maintaining a compact architecture suitable for deployment in real-world applications. To evaluate the performance of the student model, we employ the Equal Error Rate (EER) metric, which provides a balanced measure of false acceptance and false rejection rates. By analyzing EER, we can assess how well the student model generalizes to unseen spoofing attacks and its effectiveness in distinguishing between genuine and counterfeit audio. The results demonstrate that training with a single teacher model significantly enhances the student model’s performance in audio deepfake detection tasks. This study not only contributes to the ongoing research in speaker verification and spoofing countermeasures but also lays the groundwork for future explorations involving multiple teacher models and various combinations of architectures. Ultimately, this work aims to improve robustness against emerging spoofing techniques and advance the state-of-the-art in audio verification systems.
2025-11-27T00:00:00ZData driven roboticsKhade, NischayGoyal, ParthYadav, SiddharthKaul, Sanjit Krishnan (Advisor)http://repository.iiitd.edu.in/xmlui/handle/123456789/20002026-08-20T22:00:31Z2025-12-08T00:00:00ZData driven robotics
Khade, Nischay; Goyal, Parth; Yadav, Siddharth; Kaul, Sanjit Krishnan (Advisor)
Achieving dexterous and high-precision autonomous manipulation requires moving beyond pre programmed motion sequences toward adaptable, data-driven policies capable of handling envi ronmental variations. This project presents an implementation of Action Chunking Transformers (ACT), a method that enables robotic manipulators to infer appropriate motion strategies from sensory observations by predicting sequences of future actions rather than single-step trajectories. The underlying architecture utilises an encoder-decoder transformer to process visual inputs from multiple cameras alongside proprioceptive data, employing temporal ensembling to ensure smooth and temporally consistent execution. Experimental validation was conducted on an OpenManipulator-X robotic arm , utilizing a leader follower configuration to curate a dataset of 50 demonstration episodes for randomized pick-and place tasks. Although initial deployments highlighted the model’s sensitivity to visual ambiguity, subsequent optimizations in lighting, scene isolation, and visual contrast significantly enhanced policy localization and grasping robustness. Concluding with a perspective on scalability, we propose future integrations with Vision-Language-Action (VLA) models such as Pi0 and the use of depth streams to synthesize virtual camera views, thereby reducing hardware dependencies.
2025-12-08T00:00:00ZVisual voice activity detection using multimodal foundation modelsShubhamBuduru, Arun Balaji (Advisor)http://repository.iiitd.edu.in/xmlui/handle/123456789/19902026-06-17T22:46:58Z2025-07-01T00:00:00ZVisual voice activity detection using multimodal foundation models
Shubham; Buduru, Arun Balaji (Advisor)
This project explores the task of Visual Voice Activity Detection (VVAD) using only facial video data without access to audio. We evaluate the effectiveness of pretrained models including VideoMAE, ViViT, TimeSformer, ResNet50, as well as multimodal models like ImageBind, LanguageBind, and Video-LLaVA. Our goal is to classify whether a person is speaking in a given video segment using only visual cues. The models are tested on the VVAD-LRS3 dataset, and the results show strong promise for multimodal models even in vision-only setups. We hypothesize that large vision-language models can be adapted for explainable VVAD using prompt-based querying.
2025-07-01T00:00:00ZInteractive task learning framework for human-robot collaboration using generative AIGarg, Himang ChandraJain, Aditya RajShukla, Jainendra (Advisor)Kundu, Tanmoy (Advisor)http://repository.iiitd.edu.in/xmlui/handle/123456789/19692026-05-23T22:12:05Z2025-07-18T00:00:00ZInteractive task learning framework for human-robot collaboration using generative AI
Garg, Himang Chandra; Jain, Aditya Raj; Shukla, Jainendra (Advisor); Kundu, Tanmoy (Advisor)
Navigating a robot in an new environment without predefined graphs presents significant chal- lenges in perception, planning, and adaptability. However, traditional approaches rely on struc- tured maps, which limits their flex- ibility in dynamic and unexplored environments. Therefore, we propose a foundational framework that enables robots to navigate and execute tasks through human interaction in natural language. By leveraging Generative AI and multimodal learning, our system allows robots to dynamically adapt to new environments without requiring prede- fined graphs
2025-07-18T00:00:00Z