Sreyan88

GAMA

Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

MMER

Code for the InterSpeech 2023 paper: MMER: Multimodal Multi-task learning for Speech Emotion Recognition

Fatigue-Detection-using-Deep-Learning

This is a project based on a research paper to detect fatigue levels of a person through a photograph.

ReCLAP

LAPE

A unified framework for Low-resource Audio Processing and Evaluation (SSL Pre-training and Downstream Fine-tuning)

ACLM

Code for ACL 2023 Paper: ACLM: A Selective-Denoising based Generative Data Augmentation Approach for Low-Resource Complex NER

VDGD

Code for ICLR 2025 Paper: Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs

CompA

Code for ICLR 2024 Paper: CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models

LipGER

Code for InterSpeech 2024 Paper: LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition

RECAP

Code for ICASSP 2024 Paper: RECAP: Retrieval-Augmented Audio Captioning

Disfluency-Detection-with-Span-Classification

This repository contains the implementation of the paper: "Span Classification with Structured Information for Disfluency Detection in Spoken Utterances"

DALE

Code for EMNLP 2023 paper: DALE: Generative Data Augmentation for Low-Resource Legal NLP

Synthio

Code for ICLR 2025 Paper: Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Data

BioAug

Code for SIGIR 2023 paper: BioAug: Conditional Generation based Data Augmentation for Low-Resource Biomedical NER

CoDa

Code for NAACL 2024 (Findings) Paper: CoDa: Constrained Generation based Data Augmentation for Low-Resource NLP

CoSyn

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

ABEX

Code for ACL 2024 paper -- ABEX: Data Augmentation for Low-Resource NLU via Expanding Abstract Descriptions

audio-flamingo

PyTorch implementation of Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities.

Audio-QFormer

ASPIRE

gamaaudio

audio-ssl

audio_webpage

compa_iclr

M-MELD

MAST

mmau_homepage

sreyan88.github.io

My personal website and blog (http://sreyan88.github.io)

synthio_iclr

vdgd_website