people
We collectively refer to our group as CSALT (that stands for "Computational Speech and Language Technologies", and is pronounced like the word "seasalt"). I have had the pleasure of working with very talented and wonderful students over the years. The names and pages of both current and past students are listed below.
Current students
- Ashish Mittal (Research Scientist at IBM Research India and Ph.D. student at IITB co-advised with Prof. Sunita Sarawagi, Works on text-based adaptation of ASR and ASR-LLM integration)
- Barah Fazili (Ph.D. student, Works on cross-lingual NLP)
- Sona Elza Simon (Ph.D. student, Works on transfer learning using multilingual LLMs)
- Sanjeev Kumar (Ph.D. student co-advised with Prof. Pushpak Bhattacharyya, Works on extremely low-resource NLP)
- Darshan Prabhu (Ph.D. student, Works on new architectures for ASR and multimodal models)
- Abhishek Kumar Gupta (M.Tech. student, Works on multimodal learning)
- Himanshu Dutta (M.Tech. student co-advised with Prof. Pushpak Bhattacharyya, Works on RAG, agentic MT)
- Ayyagari Sathya Sai Srikar (M.Tech. student co-advised with Prof. Pushpak Bhattacharyya, Works on disfluency modeling and multimodal learning)
- Daksh Goyal (M.Tech. student, Works on parameter-efficient ASR)
- A. Snegha (M.S. student at CMInDS, Works on cross-lingual transfer learning in NLP)
- Soumen Kumar Mondal (M.S. student at CMInDS, Works on cross-lingual transfer learning in NLP)
Alumni
Postgraduate students
- Vinit Unni (Qualcomm Research, Graduated with Ph.D. in 2024, Worked on domain adaptation in ASR)
- Ashish Sunil Agrawal (IBM Research, Graduated with M.S. in 2024, Worked on cross-lingual NLP)
- Bhavani Shankar (Qualcomm, Graduated with M.Tech. in 2024, Worked on multilingual LLM prompting and spoken translation)
- Dhiraj Kumar Sah (Qualcomm, Graduated with M.Tech. in 2024, Worked on code-switched speech modeling)
- Yashwant Singh Parihar (Optym, Graduated with M.Tech. in 2024, Co-advised with Prof. Ganesh Ramakrishnan, Worked on fairness in speech)
- Saurabh Kumar (Optym, Graduated with M.Tech. in 2024, Co-advised with Prof. Ganesh Ramakrishnan, Worked on controllable speech synthesis)
- Piyush Singh Pasi (Amazon, Graduated with M.Tech. in 2023, Worked on multimodal learning)
- Vedant Singh (Couchbase, Graduated with M.Tech. in 2023, Worked on accented ASR)
- Rohit Kundu (Google, Graduated with M.Tech. in 2022, Co-advised with Prof. Pushpak Bhattacharyya, Worked on disfluency modeling)
- Mayank Kothari(IITB, Graduated with M.Tech. in 2022, Co-advised with Prof. Ganesh Ramakrishnan, Worked on ASR adaptation)
- Shubham Nemani (Qualcomm, Graduated with M.Tech. in 2022, Co-advised with Prof. Ganesh Ramakrishnan, Worked on audio-based multimodal learning)
- Pranjal Saini(Apple, Graduated with M.Tech. in 2022, Co-advised with Prof. Ganesh Ramakrishnan, Worked on audio-based multimodal learning)
- Ankita Singh(Apple, Graduated with M.Tech. in 2022, Co-advised with Prof. Kameswari Chebrolu, Worked on crowdsourcing for Indian languages)
- Nikhil Saini (Samsung Electronics, Graduated with M.Tech. in 2021, Co-advised with Prof. Pushpak Bhattacharyya, Worked on disfluency modeling and spoken translation)
- Jayaprakash Akula (Samsung R&D, Graduated with M.Tech. in 2021, Co-advised with Prof. Ganesh Ramakrishnan, Worked on video captioning and retrieval)
- Abhishek Thakur (Cohesity, Graduated with M.Tech. in 2021, Co-advised with Prof. Ganesh Ramakrishnan, Worked on video captioning and retrieval)
- Samrat Dutta (Qualcomm, Graduated with M.Tech. in 2021, Co-advised with Prof. Ganesh Ramakrishnan, Worked on memory-augmented models for MT)
- Mayur Warialani (Google, Graduated with M.Tech. in 2020, Co-advised with Prof. Ganesh Ramakrishnan, Worked on dense captioning and retrieval)
- Achari Rakesh Prashanth (Motive, Graduated with M.Tech. in 2020, Co-advised with Prof. Ganesh Ramakrishnan, Worked on dense captioning and retrieval)
- Minali Upreti (Mercedes-Benz R&D, Graduated with M.Tech. in 2019, Worked on accented ASR)
- Arijit Mukherjee (Meta, Graduated with M.Tech. in 2019, Co-advised with Prof. Ganesh Ramakrishnan, Worked on low-resource question-answering)
- Digvijaysingh Gautam (Regie, Graduated with M.Tech. in 2019, Co-advised with Prof. Ganesh Ramakrishnan, Worked on audio event detection and video summarization)
- Pankaj Joshi (Google, Graduated with M.Tech. in 2019, Co-advised with Prof. Ganesh Ramakrishnan, Worked on audio event detection and video summarization)
- Adarsh Rahul Jaju (Dista, Graduated with M.Tech. in 2019, Co-advised with Prof. Pushpak Bhattacharyya, Worked on Spoken MT)
- Abhilash Panicker (Samsung R&D, Graduated with M.Tech. in 2018, Worked on lecture ASR for Indian languages)
- Abhinav Jain (Amazon, Graduated with M.Tech. in 2018, Worked on accented ASR)
- Sanket Gandhare (Microsoft, Graduated with M.Tech. in 2018, Co-advised with Prof. Pushpak Bhattacharyya, Worked on spoken MT)
- Himanshu Agarwal (Microsoft, Graduated with M.Tech. in 2018, Worked on low-resource ASR)
Undergraduate/dual-degree students (with thesis projects or co-authored a paper)
- Amruta Mahendra Parulekar (Ph.D. student at UIUC, Graduated with dual degree, B.Tech. in EE in 2025, Worked on multimodal learning and speech synthesis)
- Ankur Verma (NK Securities, Graduated with dual degree, B.Tech. in EE in 2025, Worked on flow-based models for text-to-speech)
- Harsh Poonia (M.S. student at Carnegie Mellon University, Graduated with B.Tech. in CSE in 2025, Worked on equivariant architectures for speech)
- Sabyasachi Samanataray (Samsung Research Korea, Graduated with B.Tech. in CSE in 2025, Worked on cross-lingual NLP)
- Adyasha Patra (M.S. student at UC San Diego, Graduated with B.Tech. in CSE in 2025, Worked on code-switched speech and pathological speech processing)
- Divyansh Singhal (Quantbox, Graduated with B.Tech. in CSE in 2025, Co-advised with Prof. Soumen Chakrabarti, Worked on tokenization and transformer architectures)
- Anshul Verma (Graduated with B.Tech. in CSE in 2025, Co-advised with Prof. Soumen Chakrabarti, Worked on tokenization and transformer architectures)
- Omkar Nitsure (M.S. student at ETH Zurich, Graduated with B.Tech. in EE in 2025, Worked on accented speech and cross-lingual NLP)
- Aryan Vijay Bhosale (Graduated with B.Tech. in ME in 2025, Worked on multimodal learning)
- Sameep Chattopadhyay (Ph.D. student at University of Washington, Graduated with dual degree, B.Tech. in EE in 2025, Worked on multimodal learning)
- Azeem Azaz Motiwala (Microsoft, Graduated with B.Tech. in EE in 2025, Worked on OOD generalization of pretrained VLMs)
- Sahil Nilesh Dharod (MS in Carnegie Mellon University, Graduated with B.Tech. in EE in 2025, Worked on OOD generalization of pretrained VLMs)
- T Pavan Kalyan (Research Fellow at Microsoft Research India, Graduated with dual degree, B.Tech. in EE in 2024, Worked on expressive speech synthesis)
- Harshvardhan Agarwal (MS in Stanford University, Graduated with B.Tech. in CSE in 2024, Co-advised with Prof. Soumen Chakrabarti, Worked on tokenization in multilingual LLMs)
- Koustubh Rao (Qube Research, Graduated with B.Tech. in CSE in 2024, Co-advised with Prof. Ganesh Ramakrishnan, Worked on flow-matching models for speech synthesis)
- Govind Saju (Rubric, Graduated with B.Tech. in CSE in 2024, Worked on parameter-efficient cross-lingual NLP)
- Richeek Das (Ph.D. at University of Pennsylvania, Graduated with B.Tech. in CSE in 2023, Worked on code-switched NLP)
- Sahasra Ranjan (Co-Founder and CTO of MathCraft, Graduated with B.Tech. in CSE in 2023, Worked on code-switched NLP)
- Vineet Bhat (Ph.D. at NYU, Graduated with B.Tech. in EP in 2023, Co-advised with Prof. Pushpak Bhattacharyya, Worked on multilingual disfluency modeling)
- Anmol Reddy Mekala (MS at UMass Amherst, Graduated with B.Tech. in CSE in 2022, Co-advised with Prof. Ganesh Ramakrishnan, Worked on subset selection techniques for ASR)
- Ritika (Google, Graduated with B.Tech. in CSE in 2022, Worked on code-switched NLP)
- Shreya Pathak (Google DeepMind, Graduated with B.Tech. in CSE in 2022, Worked on code-switched NLP)
- Yash Gupta (Headlands Technologies LLC, Graduated with B.Tech. in CSE in 2022, Worked on scientific document summarization)
- Rohan Shah (Eightfold, Graduated with B.Tech. in CSE in 2022, Worked on cross-lingual NLP)
- Archiki Prasad (Ph.D. student at UN Chapel Hill, Graduated with dual degree + B.Tech. in EE in 2021, Worked on accented ASR and robust ASR)
- Anuj Jitendra Diwan (Ph.D. student at UT Austin, Graduated with B.Tech. in CSE in 2021, Worked on low-resource and multilingual ASR)
- Arjit Jain (Co-founder and CTO of TurboML, Graduated with B.Tech. in CSE in 2021, Worked on speech augmentation and low-resource image captioning)
- Soumya Chatterjee (Apple, Graduated with B.Tech. in CSE in 2021, Collaboration with Prof. Sunita Sarawagi, Worked on constraint-driven MT)
- Pranay Reddy Samala (Parallel Web Systems, Graduated with B.Tech. in CSE in 2021, Worked on speech augmentation and semi-supervised learning for ASR)
- Yash Sharma (Matic Robots, Graduated with B.Tech. in CSE in 2021, Worked on speech augmentation and semi-supervised learning for ASR)
- Drumil Trivedi (Masters in Finance at MIT, Co-advised with Prof. Sunita Sarawagi, Graduated with B.Tech. in CSE in 2021, Worked on dictionary-based adaptation for ASR)
- Mohammad Ali Rehan (FlashIntel AI, Graduated with a B.Tech. in CSE in 2021, Worked on code-switched NLP)
- Karan Taneja (Ph.D. student at Georgia Tech, Graduated with a B.Tech. in EE in 2020, Worked on code-switched speech processing)
- Ishan Tarunesh (Co-founder of TailoredAI, Graduated with a B.Tech. in CSE in 2020, Worked on code-switched text generation)
- Nitish Joshi (Ph.D. student at NYU, Graduated with a B.Tech. in CSE in 2020, Worked on accented ASR and learning with noisy labels)
- Kartik Khandelwal (Mistral AI, Graduated with a B.Tech. in CSE in 2020, Co-advised with Prof. Sunita Sarawagi, Worked on black-box adaptation of ASR)
- Syamantak Kumar (Ph.D. student at UT Austin, Graduated with a B.Tech. in CSE in 2020, Worked on code-switched NLP)
- Yash Shah (Glean, Graduated with a B.Tech. in CSE in 2020, Worked on hybrid models for LMs and active learning for speech)
- Chitwan Saharia (Co-founder of Ideogram, Graduated with a B.Tech. in CSE in 2019, Worked on multimodal audio/video learning)
- Vishwajeet Singh Bagdawat (Adobe, Graduated with a B.Tech. in CSE in 2019, Worked on multimodal audio/video learning)
- Kalpesh Krishna (Google DeepMind, Graduated with a B.Tech. in EE in 2018, Worked on neural LMs and constraint-driven learning)
- Saurabh Garg (Thinking Machines Lab, Graduated with a B.Tech. in CSE in 2018, Worked on code-switched speech and NLP)
- Tanmay Parekh (Ph.D. student at UCLA, Graduated with a B.Tech. in CSE in 2018, Worked on code-switched speech and NLP)
- Suman Swaroop (Rubrik, Graduated with a B.Tech. in CSE in 2018, Worked on crowdsourcing for speech in Indian languages)
- Rajat Chaturvedi (Gaja Capital, Graduated with a B.Tech. in CSE in 2018, Worked on crowdsourcing for speech in Indian languages)
- Jayanth Shankar Chennareddy (ImagoAI, Graduated with a B.Tech. in CSE in 2018, Worked on low-resource multilingual ASR)
- Mohit Vyas (Microsoft, Graduated with a B.Tech. in CSE in 2018, Worked on accent identification from speech)
- Sohum Dhar (Rubrik, Graduated with a B.Tech. in CSE in 2018, Worked on attention-based models for ASR)