sonalkum (Sonal Kumar)

authored 3 papers 2 months ago

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

Paper • 2410.02056 • Published Oct 2, 2024 • 6

Do Audio-Language Models Understand Linguistic Variations?

Paper • 2410.16505 • Published Oct 21, 2024 • 1

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

Paper • 2410.19168 • Published Oct 24, 2024 • 19

upvoted a paper 2 months ago

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

Paper • 2410.19168 • Published Oct 24, 2024 • 19

updated a Space 2 months ago

Running on Zero

11

📚

Synthio Stable Audio Open

Stable audio open model from Synthio paper.

updated a model 2 months ago

sonalkum/synthio-t5

Updated Oct 26, 2024

updated a model 3 months ago

sonalkum/synthio-stable-audio-open

Updated Oct 19, 2024 • 2

upvoted a paper 3 months ago

Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation

Paper • 2410.13198 • Published Oct 17, 2024 • 9

authored a paper 4 months ago

ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds

Paper • 2409.09213 • Published Sep 13, 2024 • 12

upvoted a paper 4 months ago

ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds

Paper • 2409.09213 • Published Sep 13, 2024 • 12

updated 2 Spaces 6 months ago

Running on Zero

13

🌍

GAMA

Running on Zero

4

🏆

GAMA-IT

liked 2 Spaces 6 months ago

Running on Zero

4

🏆

GAMA-IT

Running on Zero

13

🌍

GAMA

authored 6 papers 7 months ago

VDGD: Mitigating LVLM Hallucinations in Cognitive Prompts by Bridging the Visual Perception Gap

Paper • 2405.15683 • Published May 24, 2024

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

Paper • 2404.00415 • Published Mar 30, 2024

Sonal Kumar

AI & ML interests

Organizations

sonalkum's activity

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

Do Audio-Language Models Understand Linguistic Variations?

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

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

Synthio Stable Audio Open

sonalkum/synthio-t5

sonalkum/synthio-stable-audio-open

Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation

ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds

ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds

GAMA

GAMA-IT

GAMA-IT

GAMA

ASPIRE: Language-Guided Augmentation for Robust Image Classification

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

DALE: Generative Data Augmentation for Low-Resource Legal NLP

A Closer Look at the Limitations of Instruction Tuning

VDGD: Mitigating LVLM Hallucinations in Cognitive Prompts by Bridging the Visual Perception Gap

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