34 citations · 72 across the 11 of their papers we have counts for
11 papers
Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings
Aakriti Agrawal, Gouthaman KV, Rohith Aralikatti +6
Hallucinations in Large Vision-Language Models (LVLMs) remain a persistent challenge, often stemming from inadequate integration of visual information during multimodal reasoning.…
Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
Aakriti Agrawal, Rohith Aralikatti, Anirudh Satheesh +3
Large Language Models (LLMs) have demonstrated exceptional capabilities, yet selecting the most reliable response from multiple LLMs remains a challenge, particularly in resource-c…
Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning
Aakriti Agrawal, Rohith Aralikatti, Yanchao Sun +1
Multi-agent reinforcement learning (MARL) plays a pivotal role in tackling real-world challenges. However, the seamless transition of trained policies from simulations to real-worl…
Synthetic Wave-Geometric Impulse Responses for Improved Speech Dereverberation
Rohith Aralikatti, Zhenyu Tang, Dinesh Manocha
We present a novel approach to improve the performance of learning-based speech dereverberation using accurate synthetic datasets. Our approach is designed to recover the reverb-fr…
Reverberation as Supervision for Speech Separation
Rohith Aralikatti, Christoph Boeddeker, Gordon Wichern +2
This paper proposes reverberation as supervision (RAS), a novel unsupervised loss function for single-channel reverberant speech separation. Prior methods for unsupervised separati…
MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
Anton Ratnarajah, Zhenyu Tang, Rohith Chandrashekar Aralikatti +1
We propose a mesh-based neural network (MESH2IR) to generate acoustic impulse responses (IRs) for indoor 3D scenes represented using a mesh. The IRs are used to create a high-quali…
GWA: A Large High-Quality Acoustic Dataset for Audio Processing
Zhenyu Tang, Rohith Aralikatti, Anton Ratnarajah +1
We present the Geometric-Wave Acoustic (GWA) dataset, a large-scale audio dataset of about 2 million synthetic room impulse responses (IRs) and their corresponding detailed geometr…
Improving Reverberant Speech Separation with Multi-stage Training and Curriculum Learning
Rohith Aralikatti, Anton Ratnarajah, Zhenyu Tang +1
We present a novel approach that improves the performance of reverberant speech separation. Our approach is based on an accurate geometric acoustic simulator (GAS) which generates…
Audio-Visual Decision Fusion for WFST-based and seq2seq Models
Rohith Aralikatti, Sharad Roy, Abhinav Thanda +4
Under noisy conditions, speech recognition systems suffer from high Word Error Rates (WER). In such cases, information from the visual modality comprising the speaker lip movements…
LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models
Dilip Kumar Margam, Rohith Aralikatti, Tanay Sharma +4
In recent years, deep learning based machine lipreading has gained prominence. To this end, several architectures such as LipNet, LCANet and others have been proposed which perform…
Global SNR Estimation of Speech Signals using Entropy and Uncertainty Estimates from Dropout Networks
Rohith Aralikatti, Dilip Margam, Tanay Sharma +2
This paper demonstrates two novel methods to estimate the global SNR of speech signals. In both methods, Deep Neural Network-Hidden Markov Model (DNN-HMM) acoustic model used in sp…