Scholar
Satvik Dixit
Google Scholar ID: fO8a44AAAAAJ
Carnegie Mellon University
Speech and Audio
Large Language Models
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
23
H-index
2
i10-index
0
Publications
7
Co-authors
4
list available
Contact
Email
satvikdixit@cmu.edu
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
5 items
FoleyBench: A Benchmark For Video-to-Audio Models
2025
Cited
0
AURA Score: A Metric For Holistic Audio Question Answering Evaluation
2025
Cited
0
MMAU-Pro: A Challenging and Comprehensive Benchmark for Holistic Evaluation of Audio General Intelligence
2025
Cited
0
Learning Perceptually Relevant Temporal Envelope Morphing
2025
Cited
0
Mellow: a small audio language model for reasoning
2025
Cited
0
Resume (English only)
Academic Achievements
- Mellow: a small audio language model for reasoning (NeurIPS 2025)
- MACE: Leveraging Audio for Evaluating Audio Captioning Systems (ICASSP 2025 SALMA Workshop)
- Vision Language Models Are Few-Shot Audio Spectrogram Classifiers (NeuRIPS 2024 Audio Imagination Workshop)
Research Experience
- Worked with Professor Chris Donahue on Generative Audio
- Worked with Professor Bhiksha Raj on Audio Language Models
- Interned with Dr. Satrajit Ghosh at MIT
- Interned with Dr. Martin Vetterli at EPFL
Education
Undergraduate degree in Electrical Engineering from IIT Delhi, with a concentration on signals processing and ML.
Background
Master's student at Carnegie Mellon University, interested in audio understanding and generation.
Miscellany
Email: satvikdixit@cmu.edu
Google Scholar: Google Scholar
LinkedIn: LinkedIn
Co-authors
4 total
Bhiksha Raj
Carnegie Mellon University
Soham Deshmukh
Microsoft, Carnegie Mellon University
Chris Donahue
Assistant Professor, CMU CSD; Research Scientist, Google DeepMind (part time)
Satrajit Ghosh
Senior Research Scientist, MIT; Assistant Professor, HMS
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up