15 citations · 20 across the 27 of their papers we have counts for
29 papers
Making LoRA Identifiable: Orthogonal Alignment for Continual Learning
Pratik Rakesh Singh, Mohammadi Zaki, Akash Saha +2
There is growing interest in applying Parameter-Efficient Fine-Tuning (PEFT) to Continual Learning, as it enables faster training, mitigates catastrophic forgetting, and facilitate…
Can Hierarchical Cross-Modal Fusion Predict Human Perception of AI Dubbed Content?
Ashwini Dasare, Nirmesh Shah, Ashishkumar Gudmalwar +1
Evaluating AI generated dubbed content is inherently multi-dimensional, shaped by synchronization, intelligibility, speaker consistency, emotional alignment, and semantic context.…
EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer
Munish Monga, Vishal Chudasama, Pankaj Wasnik +1
Real-world object detection must operate in evolving environments where new classes emerge, domains shift, and unseen objects must be identified as "unknown": all without accessing…
Gesture2Speech: How Far Can Hand Movements Shape Expressive Speech?
Lokesh Kumar, Nirmesh Shah, Ashishkumar P. Gudmalwar +1
Human communication seamlessly integrates speech and bodily motion, where hand gestures naturally complement vocal prosody to express intent, emotion, and emphasis. While recent te…
Face Time Traveller : Travel Through Ages Without Losing Identity
Purbayan Kar, Ayush Ghadiya, Vishal Chudasama +2
Face aging, an ill-posed problem shaped by environmental and genetic factors, is vital in entertainment, forensics, and digital archiving, where realistic age transformations must…
Windowed SummaryMixing: An Efficient Fine-Tuning of Self-Supervised Learning Models for Low-resource Speech Recognition
Aditya Srinivas Menon, Kumud Tripathi, Raj Gohil +1
Self-supervised learning (SSL) has advanced speech processing but suffers from quadratic complexity due to self-attention. To address this, SummaryMixing (SM) has been proposed as…
Listen Like a Teacher: Mitigating Whisper Hallucinations using Adaptive Layer Attention and Knowledge Distillation
Kumud Tripathi, Aditya Srinivas Menon, Aman Gaurav +2
The Whisper model, an open-source automatic speech recognition system, is widely adopted for its strong performance across multilingual and zero-shot settings. However, it frequent…
DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic
Munish Monga, Vishal Chudasama, Pankaj Wasnik +1
Real-world object detection systems, such as those in autonomous driving and surveillance, must continuously learn new object categories and simultaneously adapt to changing enviro…
LASPA: Language Agnostic Speaker Disentanglement with Prefix-Tuned Cross-Attention
Aditya Srinivas Menon, Raj Prakash Gohil, Kumud Tripathi +1
Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits s…
Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion
Kumud Tripathi, Chowdam Venkata Kumar, Pankaj Wasnik
Voice Activity Detection (VAD) plays a key role in speech processing, often utilizing hand-crafted or neural features. This study examines the effectiveness of Mel-Frequency Cepstr…
Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages
Pratik Rakesh Singh, Kritarth Prasad, Mohammadi Zaki +1
Translating multi-word expressions (MWEs) and idioms requires a deep understanding of the cultural nuances of both the source and target languages. This challenge is further amplif…
REWIND: Speech Time Reversal for Enhancing Speaker Representations in Diffusion-based Voice Conversion
Ishan D. Biyani, Nirmesh J. Shah, Ashishkumar P. Gudmalwar +2
Speech time reversal refers to the process of reversing the entire speech signal in time, causing it to play backward. Such signals are completely unintelligible since the fundamen…
In-Domain African Languages Translation Using LLMs and Multi-armed Bandits
Pratik Rakesh Singh, Kritarth Prasad, Mohammadi Zaki +1
Neural Machine Translation (NMT) systems face significant challenges when working with low-resource languages, particularly in domain adaptation tasks. These difficulties arise due…
Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance
Sanchayan Santra, Vishal Chudasama, Pankaj Wasnik +1
Precise Event Spotting (PES) aims to identify events and their class from long, untrimmed videos, particularly in sports. The main objective of PES is to detect the event at the ex…
Faster Machine Translation Ensembling with Reinforcement Learning and Competitive Correction
Kritarth Prasad, Mohammadi Zaki, Pratik Singh +1
Ensembling neural machine translation (NMT) models to produce higher-quality translations than the individual models has been extensively studied. Recent methods typically empl…
Open-Set Object Detection By Aligning Known Class Representations
Hiran Sarkar, Vishal Chudasama, Naoyuki Onoe +2
Open-Set Object Detection (OSOD) has emerged as a contemporary research direction to address the detection of unknown objects. Recently, few works have achieved remarkable performa…
Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection
Ayush Ghadiya, Purbayan Kar, Vishal Chudasama +1
Recently, weakly supervised video anomaly detection (WS-VAD) has emerged as a contemporary research direction to identify anomaly events like violence and nudity in videos using on…
Enhancing Entertainment Translation for Indian Languages using Adaptive Context, Style and LLMs
Pratik Rakesh Singh, Mohammadi Zaki, Pankaj Wasnik
We address the challenging task of neural machine translation (NMT) in the entertainment domain, where the objective is to automatically translate a given dialogue from a source la…
EmoReg: Directional Latent Vector Modeling for Emotional Intensity Regularization in Diffusion-based Voice Conversion
Ashishkumar Gudmalwar, Ishan D. Biyani, Nirmesh Shah +2
The Emotional Voice Conversion (EVC) aims to convert the discrete emotional state from the source emotion to the target for a given speech utterance while preserving linguistic con…
Enhancing Whisper's Accuracy and Speed for Indian Languages through Prompt-Tuning and Tokenization
Kumud Tripathi, Raj Gothi, Pankaj Wasnik
Automatic speech recognition has recently seen a significant advancement with large foundational models such as Whisper. However, these models often struggle to perform well in low…
Beyond Few-shot Object Detection: A Detailed Survey
Vishal Chudasama, Hiran Sarkar, Pankaj Wasnik +2
Object detection is a critical field in computer vision focusing on accurately identifying and locating specific objects in images or videos. Traditional methods for object detecti…
DubWise: Video-Guided Speech Duration Control in Multimodal LLM-based Text-to-Speech for Dubbing
Neha Sahipjohn, Ashishkumar Gudmalwar, Nirmesh Shah +2
Audio-visual alignment after dubbing is a challenging research problem. To this end, we propose a novel method, DubWise Multi-modal Large Language Model (LLM)-based Text-to-Speech…
VECL-TTS: Voice identity and Emotional style controllable Cross-Lingual Text-to-Speech
Ashishkumar Gudmalwar, Nirmesh Shah, Sai Akarsh +2
Despite the significant advancements in Text-to-Speech (TTS) systems, their full utilization in automatic dubbing remains limited. This task necessitates the extraction of voice id…
Efficient infusion of self-supervised representations in Automatic Speech Recognition
Darshan Prabhu, Sai Ganesh Mirishkar, Pankaj Wasnik
Self-supervised learned (SSL) models such as Wav2vec and HuBERT yield state-of-the-art results on speech-related tasks. Given the effectiveness of such models, it is advantageous t…