papers

Publications (37)

cs.SD2024

GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

Sreyan Ghosh, Sonal Kumar, Ashish Seth +6

Perceiving and understanding non-speech sounds and non-verbal speech is essential to making decisions that help us interact with our surroundings. In this paper, we propose GAMA, a…

cs.CL2021

Cisco at AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides using Contextualized Embeddings

Sreyan Ghosh, Sonal Kumar, Harsh Jalan +2

This paper describes our proposed system for the AAAI-CAD21 shared task: Predicting Emphasis in Presentation Slides. In this specific task, given the contents of a slide we are ask…

cs.CL2023

DALE: Generative Data Augmentation for Low-Resource Legal NLP

Sreyan Ghosh, Chandra Kiran Evuru, Sonal Kumar +4

We present DALE, a novel and effective generative Data Augmentation framework for low-resource LEgal NLP. DALE addresses the challenges existing frameworks pose in generating effec…

eess.AS2025

Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data

Sreyan Ghosh, Sonal Kumar, Zhifeng Kong +3

We present Synthio, a novel approach for augmenting small-scale audio classification datasets with synthetic data. Our goal is to improve audio classification accuracy with limited…

cs.LG2023

CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network

Sreyan Ghosh, Manan Suri, Purva Chiniya +3

The tremendous growth of social media users interacting in online conversations has led to significant growth in hate speech, affecting people from various demographics. Most of th…

eess.AS2025

MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence

Sonal Kumar, Šimon Sedláček, Vaibhavi Lokegaonkar +31

Audio comprehension-including speech, non-speech sounds, and music-is essential for achieving human-level intelligence. Consequently, AI agents must demonstrate holistic audio unde…

eess.AS2024

ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds

Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru +3

Open-vocabulary audio-language models, like CLAP, offer a promising approach for zero-shot audio classification (ZSAC) by enabling classification with any arbitrary set of categori…

cs.CV2026

C-LEAD: Contrastive Learning for Enhanced Adversarial Defense

Suklav Ghosh, Sonal Kumar, Arijit Sur

Deep neural networks (DNNs) have achieved remarkable success in computer vision tasks such as image classification, segmentation, and object detection. However, they are vulnerable…

cs.CV2025

Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs

Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar +4

Large Vision-Language Models (LVLMs) often produce responses that misalign with factual information, a phenomenon known as hallucinations. While hallucinations are well-studied, th…

cs.SD2024

EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning

Ashish Seth, Ramaneswaran Selvakumar, S Sakshi +3

In this paper, we present EH-MAM (Easy-to-Hard adaptive Masked Acoustic Modeling), a novel self-supervised learning approach for speech representation learning. In contrast to the…

eess.AS2024

MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark

S Sakshi, Utkarsh Tyagi, Sonal Kumar +6

The ability to comprehend audio--which includes speech, non-speech sounds, and music--is crucial for AI agents to interact effectively with the world. We present MMAU, a novel benc…

cs.SD2026

Audio Hallucination Attacks: Probing the Reliability of Large Audio Language Models

Ashish Seth, Sonal Kumar, Ramaneswaran Selvakumar +5

Large Audio Language Models (LALMs) achieve strong performance on audio-language tasks; however, their reliability in real-world settings remains underexplored. We introduce Audio…

cs.SD2026

TAC: Timestamped Audio Captioning

Sonal Kumar, Prem Seetharaman, Ke Chen +8

Large Audio Language Models struggle to disentangle overlapping events in complex acoustic scenes, yielding temporally inconsistent captions and frequent hallucinations. We introdu…

eess.AS2024

RECAP: Retrieval-Augmented Audio Captioning

Sreyan Ghosh, Sonal Kumar, Chandra Kiran Reddy Evuru +2

We present RECAP (REtrieval-Augmented Audio CAPtioning), a novel and effective audio captioning system that generates captions conditioned on an input audio and other captions simi…

cs.SD2025

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

Arushi Goel, Sreyan Ghosh, Jaehyeon Kim +8

We present Audio Flamingo 3 (AF3), a fully open state-of-the-art (SOTA) large audio-language model that advances reasoning and understanding across speech, sound, and music. AF3 in…

cs.CL2024

A Closer Look at the Limitations of Instruction Tuning

Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar +5

Instruction Tuning (IT), the process of training large language models (LLMs) using instruction-response pairs, has emerged as the predominant method for transforming base pre-trai…

cs.SD2024

CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models

Sreyan Ghosh, Ashish Seth, Sonal Kumar +7

A fundamental characteristic of audio is its compositional nature. Audio-language models (ALMs) trained using a contrastive approach (e.g., CLAP) that learns a shared representatio…

cs.SD2025

Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities

Sreyan Ghosh, Zhifeng Kong, Sonal Kumar +6

Understanding and reasoning over non-speech sounds and music are crucial for both humans and AI agents to interact effectively with their environments. In this paper, we introduce…

cs.CV2024

DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer

Sonal Kumar, Arijit Sur, Rashmi Dutta Baruah

Successive proposals of several self-supervised training schemes continue to emerge, taking one step closer to developing a universal foundation model. In this process, the unsuper…

cs.AI2025

EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding

Ashish Seth, Utkarsh Tyagi, Ramaneswaran Selvakumar +6

Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in complex multimodal tasks. While MLLMs excel at visual perception and reasoning in third-person…

cs.MM2025

MultiVox: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions

Ramaneswaran Selvakumar, Ashish Seth, Nishit Anand +4

The rapid progress of Large Language Models (LLMs) has empowered omni models to act as voice assistants capable of understanding spoken dialogues. These models can process multimod…

cs.SD2024

AV-RIR: Audio-Visual Room Impulse Response Estimation

Anton Ratnarajah, Sreyan Ghosh, Sonal Kumar +2

Accurate estimation of Room Impulse Response (RIR), which captures an environment's acoustic properties, is important for speech processing and AR/VR applications. We propose AV-RI…

cs.CL2022

A novel multimodal dynamic fusion network for disfluency detection in spoken utterances

Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar +2

Disfluency, though originating from human spoken utterances, is primarily studied as a uni-modal text-based Natural Language Processing (NLP) task. Based on early-fusion and self-a…

cs.CL2024

CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP

Chandra Kiran Reddy Evuru, Sreyan Ghosh, Sonal Kumar +3

We present CoDa (Constrained Generation based Data Augmentation), a controllable, effective, and training-free data augmentation technique for low-resource (data-scarce) NLP. Our a…

cs.CL2021

Cisco at SemEval-2021 Task 5: What's Toxic?: Leveraging Transformers for Multiple Toxic Span Extraction from Online Comments

Sreyan Ghosh, Sonal Kumar

Social network platforms are generally used to share positive, constructive, and insightful content. However, in recent times, people often get exposed to objectionable content lik…

cs.SD2024

PAT: Parameter-Free Audio-Text Aligner to Boost Zero-Shot Audio Classification

Ashish Seth, Ramaneswaran Selvakumar, Sonal Kumar +2

Audio-Language Models (ALMs) have demonstrated remarkable performance in zero-shot audio classification. In this paper, we introduce PAT (Parameter-free Audio-Text aligner), a simp…

cs.CV2024

ASPIRE: Language-Guided Data Augmentation for Improving Robustness Against Spurious Correlations

Sreyan Ghosh, Chandra Kiran Reddy Evuru, Sonal Kumar +4

Neural image classifiers can often learn to make predictions by overly relying on non-predictive features that are spuriously correlated with the class labels in the training data.…

cs.SD2024

SILA: Signal-to-Language Augmentation for Enhanced Control in Text-to-Audio Generation

Sonal Kumar, Prem Seetharaman, Justin Salamon +2

The field of text-to-audio generation has seen significant advancements, and yet the ability to finely control the acoustic characteristics of generated audio remains under-explore…

cs.CL2022

Span Classification with Structured Information for Disfluency Detection in Spoken Utterances

Sreyan Ghosh, Sonal Kumar, Yaman Kumar Singla +2

Existing approaches in disfluency detection focus on solving a token-level classification task for identifying and removing disfluencies in text. Moreover, most works focus on leve…

cs.CV2024

Do Vision-Language Models Understand Compound Nouns?

Sonal Kumar, Sreyan Ghosh, S Sakshi +2

Open-vocabulary vision-language models (VLMs) like CLIP, trained using contrastive loss, have emerged as a promising new paradigm for text-to-image retrieval. However, do VLMs unde…

eess.AS2025

ProSE: Diffusion Priors for Speech Enhancement

Sonal Kumar, Sreyan Ghosh, Utkarsh Tyagi +4

Speech enhancement (SE) is the foundational task of enhancing the clarity and quality of speech in the presence of non-stationary additive noise. While deterministic deep learning…

cs.CL2023

BioAug: Conditional Generation based Data Augmentation for Low-Resource Biomedical NER

Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar +1

Biomedical Named Entity Recognition (BioNER) is the fundamental task of identifying named entities from biomedical text. However, BioNER suffers from severe data scarcity and lacks…

cs.SD2025

Do Audio-Language Models Understand Linguistic Variations?

Ramaneswaran Selvakumar, Sonal Kumar, Hemant Kumar Giri +4

Open-vocabulary audio language models (ALMs), like Contrastive Language Audio Pretraining (CLAP), represent a promising new paradigm for audio-text retrieval using natural language…

cs.CL2023

ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NER

Sreyan Ghosh, Utkarsh Tyagi, Manan Suri +3

Complex Named Entity Recognition (NER) is the task of detecting linguistically complex named entities in low-context text. In this paper, we present ACLM Attention-map aware keywor…

eess.AS2024

LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition

Sreyan Ghosh, Sonal Kumar, Ashish Seth +4

Visual cues, like lip motion, have been shown to improve the performance of Automatic Speech Recognition (ASR) systems in noisy environments. We propose LipGER (Lip Motion aided Ge…

cs.SD2026

Multi-Domain Audio Question Answering Benchmark Toward Acoustic Content Reasoning

Chao-Han Huck Yang, Sreyan Ghosh, Qing Wang +14

We present Task 5 of the DCASE 2025 Challenge: an Audio Question Answering (AQA) benchmark spanning multiple domains of sound understanding. This task defines three QA subsets (Bio…

cs.CL2024

ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions

Sreyan Ghosh, Utkarsh Tyagi, Sonal Kumar +4

We present ABEX, a novel and effective generative data augmentation methodology for low-resource Natural Language Understanding (NLU) tasks. ABEX is based on ABstract-and-EXpand, a…