Prof. Dinesh Manocha
Prof. Dinesh Manocha
Paul Chrisman Iribe Professor · University of Maryland

Prof. Dinesh Manocha is the Paul Chrisman Iribe Endowed Professor of Computer Science at the University of Maryland. He leads the GAMMA Lab, where his research focuses on audio general intelligence — developing AI systems that understand, reason, and interact with the acoustic world. His work spans audio language models, multimodal learning, self-supervised audio representation, and evaluation benchmarks. He has published over 600 papers and has received numerous awards including the ACM Fellow, IEEE Fellow, and NSF Career Award.

PhD Students
Sakshi
Sakshi
PhD Student
Audio language models, benchmarks, audio understanding evaluation
Sreyan Ghosh
Sreyan Ghosh
PhD Student
Audio-language models, self-supervised learning, audio-text alignment
Sonal Kumar
Sonal Kumar
PhD Student
Audio language models, speech enhancement, audio generation
Ashish Seth
Ashish Seth
PhD Student
Audio-text alignment, domain adaptation, knowledge distillation
Nishit Anand
Nishit Anand
PhD Student
Target speaker extraction, audio-text models
Ramaneswaran S.
Ramaneswaran S.
PhD Student
Audio-text contrastive learning, robust audio representations
Masters Students
Aryan Vijay Bhosale
Aryan Vijay Bhosale
Masters Student
Audio-language models, multimodal learning
Apoorva Anand Kulkarni
Apoorva Anand Kulkarni
Masters Student
Multimodal audio understanding
Kaousheik Jayakumar
Kaousheik Jayakumar
Masters Student
Audio generation, data augmentation
Vaibhavi Lokegaonkar
Vaibhavi Lokegaonkar
Masters Student
Speech and audio processing
Alumni
Utkarsh Tyagi
Research Engineer · Scale AI
Chandra Kiran Reddy Evuru
Senior Software Engineer · ServiceNow