Research

My research focuses on deep learning for audio processing, with a focus on building efficient models and the integration of language as a tool to improve the performance of audio processing tasks.

I am always open to collaborations, and please feel free to drop me a mail!

Google Scholar

Pre-prints

• GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities
  Sreyan Ghosh*, Sonal Kumar*, Ashish Seth, Chandra Kiran Reddy Evuru, Utkarsh Tyagi, S Sakshi, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
  Project Website / Summary Tweet / Coverage 1 / Coverage 2
  Pre-print

• EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning
  Ashish Seth*, Ramaneswaran S*, S Sakshi*, Sonal Kumar, Dinesh Manocha
  Pre-print

Accepted Papers

• ASPIRE: Language-Guided Augmentation for Robust Image Classification
  Sreyan Ghosh*, Chandra Kiran Reddy Evuru*, Sonal Kumar*, S Sakshi, Utkarsh Tyagi, Dinesh Manocha
  Code / Poster
  ACL 2024 Findings

• Do Vision-Language Models Understand Compound Nouns?
  Sonal Kumar*, Sreyan Ghosh*, S Sakshi, Utkarsh Tyagi, Dinesh Manocha
  Code / Poster
  NAACL 2024

• DALE: Generative Data Augmentation for Low-Resource Legal NLP
  Sreyan Ghosh*, Chandra Kiran Reddy Evuru*, Sonal Kumar, Ramaneswaran S, S Sakshi, Utkarsh Tyagi, Dinesh Manocha
  Code / Poster
  EMNLP 2023

• CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models
  Sreyan Ghosh*, Ashish Seth*, Sonal Kumar*, Utkarsh Tyagi*, Chandra Kiran Reddy Evuru*, Ramaneswaran S, S Sakshi, Oriol Nieto, Ramani Duraiswami, Dinesh Manocha
  Project Webiste / Slides / Poster
  ICLR 2024

• DeToxy: A Large-Scale Multimodal Dataset for Toxicity Classification in Spoken Utterances
  Sreyan Ghosh, Samden Lepcha, Sakshi, Rajiv Ratn Shah, S. Umesh
  Code / Data
  Interspeech 2022