People

Dr. Najuk Parekh has been a Postdoctoral Researcher at Dhirubhai Ambani University (DAU) since February 2026. She received her Ph.D. and M.E. degrees from Gujarat Technological University, Gujarat, and her B.E. degree from R. C. Patel Institute of Technology, North Maharashtra University, Shirpur, Maharashtra. Her research interests include speech signal processing, with a particular focus on dysarthric speech enhancement and the assessment of speech quality and intelligibility using signal-processing and deep-learning techniques.

Dr. Guman Kanwar Shekhawat is a Post-Doctoral Fellow (since February 2026) at Dhirubhai Ambani University under Professor (Dr.) Hemant A. Patil for The Meity Funded Govt. Project NLTM-Bhashini 1.0. She has completed her Ph.D. from Malaviya National Institute of Technology, Jaipur (MNIT, Jaipur) with specialization in Wireless Communication and 5G-NOMA based modelling in Cognitive Radio in 2025. She has published two SCI, Scopus indexed journal and five IEEE conferences papers and one best paper award by IIT-Patna. She has completed her M. Tech from Laxmi Niwas Mittal Institute of Information and Technology (LNMIIT, Jaipur) and B.Tech from RTU Kota. The research interest includes signal processing based algorithm design in speech communication, dysarthria severity classification, wireless communication, spectrum sensing modeling, 5G CD-NOMA. She has qualified UGC-NET and GATE-2014 and awarded UGC-scholarship.

He is a Ph.D. candidate at Dhirubhai Ambani University, working in speech and language technology. He completed my B.E. from Gujarat Technological University and my M.Tech. from Nirma University. He loves learning about and exploring speech synthesis, text-to-speech, voice conversion, and conversational AI. His research focuses on developing efficient speech systems for low-resource Indic languages in order to create inclusive voice technologies that make human–computer communication more natural and accessible.

I am a PhD researcher in Speech AI at Dhirubhai Ambani University (DAU, formerly DA-IICT), Gandhinagar, working under Prof. Patil, primarily on audio deepfake detection, attribution, and forensics. My research interest lies in bridging classical signal processing with modern deep learning to build robust, generalizable, and explainable systems for detecting synthetic and manipulated speech across languages, generators, and real-world conditions. I have authored over 20 publications in venues including IEEE Signal Processing Letters, Speech Communication, INTERSPEECH, ICASSP, and APSIPA, spanning contributions such as wavelet-integrated neural architectures (WIN), Kolmogorov-Arnold Networks for voice liveness detection, and multilingual benchmark datasets like MLADDC and SingFox. Beyond deepfake detection, my work extends to broader speech topics such as, infant cry classification, dysarthric speech analysis, spoken language identification, and hearing-aid noise reduction. I previously interned at Samsung Research Institute Bangalore (SRI-B), where I worked on real-time voice liveness detection, and have collaborated on projects under the National Language Translation Mission (NLTM) and Samsung PRISM. I am an IEEE Student Member (and SPS member), ISCA member, and a recipient of the 1st position at ICASSP MSP Cup 2024, alongside a research grant from various conferences such as, ICPR 2024, APSIPA 2025, and INDOML 2025. Outside the lab, I am an accomplished sports person with multiple national and international medals spacing across various sports.

I have done a summer research project and a mini B.Tech project during my undergraduate studies under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India.

Ms. Priyanka Gupta is a Ph.D. student (since July 2017) at Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT, Gandhinagar). She completed M. Tech. from Laxmi Niwas Mittal Institute of Information and Technology (LNMIIT, Jaipur) in 2017. Her research interest is in the protection of voice biometrics systems from spoofing attacks (specifically replay attacks and liveness detection), using signal processing based approaches in tandem with deep learning.

Mr. Ankur Patil was a Ph.D. student at DA-IICT , Gandhinagar .  he Completed his phd in Handcrafted Features for Anti-Spoofing under the supervision of  Prof. Hemant A. Patil. His research interest in  the DeepFake Detection using Audio. Google Scholar 

Ms. Madhu Kamble was a Ph.D. student at DA-IICT, Gandhinagar.  She did her M. Tech. from Cummins College of Engineering, Pune, Maharashtra in the year 2015 in Signal Processing engineering and B.Tech from P.V.P.I.T, Budhgaon, Sangli, Maharashtra in the year 2012. She has been awarded Rajiv Gandhi National Fellowship (RGNF) for her doctoral studies. Her research interest is in the Analysis of Spoofing with Signal processing aspects. Google Scholar

Dr. Hardik B. Sailor was a PhD student (since January 2013) and senior research assistant at DeitY TTS sponsored consortium project at DA-IICT. He completed his M.Tech in Information and Communication Technology (ICT) from DA-IICT, Gandhinagar, in 2013. His research areas include Deep Architectures, Automatic Speech Recognition (ASR) and Text-to-Speech Synthesis (TTS). Google Scholar

Dr. Tanvina B. Patel was a PhD student and senior research assistant at DeitY TTS sponsored consortium project at DA-IICT, Gandhinagar (June 2012 to present). She completed her Masters from L.D. College Engineering, Ahmedabad. Her research interests include analysis of nonlinearities in speech signal processing, Text-to-speech synthesis (TTS) and analysis of natural and synthetic speech using prosodic features. Google Scholar

I am pursuing my M.Tech under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information Technology (DA-IIT), Gandhinagar, Gujarat, India. I completed my B.E. (Computer Engineering) from G. H. Patel College of Engineering and Technology ,  V. V. Nagar, Anand, Gujarat, India.

I am pursuing my M.Tech under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information Technology (DA-IIT), Gandhinagar, Gujarat, India. I completed my B.E. (Electronics and communication) from Vishwakarma Government Engineering College, Chandkheda, Ahmedabad, Gujarat, India.

My research interest focuses on the development of countermeasure systems against various spoofing attacks on Automatic Speaker Verification (ASV) systems, using speech signal processing and deep learning aspects.

I am pursuing my M.Tech under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information Technology (DA-IIT), Gandhinagar, Gujarat, India. I completed my B.E. (Electronics and communication) from Vishwakarma Government Engineering College, Chandkheda, Ahmedabad, Gujarat, India.

My research interest focuses on the development of countermeasure systems against various spoofing attacks on Automatic Speaker Verification (ASV) systems, using speech signal processing and deep learning aspects.

I am pursuing my M.Tech under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information Technology (DA-IICT), Gandhinagar, Gujarat, India. I completed my B.Tech (Electronics and communication) from Dharmsinh Desai University Nadiad, Gujarat, India.

Currently working on designing countermeasure systems for spoof detection for Voice Assistants and Automatic Verification systems using deep learning and speech signal processing methodologies.

I am pursuing my M.Tech under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information Technology (DA-IICT), Gandhinagar, Gujarat, India. I completed my B.E. (Electronics and communication) from LD College of Engineering, Ahmedabad, Gujarat, India.

My research interest focuses on Infant cry analysis for Healthy vs. Pathological cries, using speech signal processing and deep learning aspects.

I am pursuing my M.Tech under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information Technology (DA-IICT), Gandhinagar, Gujarat, India. I completed my B.Tech (Electronics and communication) from Vishwakarma Government Engineering College, GTU.

Currently working on Automatic Speech Recognition technology using Self-Supervised Learning techniques.  As well as Language Modeling and Acoustic Modeling.

I have graduated with my M.Tech. under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India. I completed my B.E. in Electrical Engineering from Ujjain Engineering College, Ujjain, M.P., India.

My research area focuses on the development of a countermeasure system against Spoof Speech Detection for Voice Assistance and Automatic Speaker Verification (ASV) systems, Classification of Whisper vs. Normal Speech, Voice Liveness Detection systems for improvement of accuracy and reliability of ASV systems.

I have graduated with my M.Tech. under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India. I completed my B.E. in Electronics and Communication Engineering from Shri Vaishnav Institute of Technology and Science, Indore, Madhya Pradesh, India.

My research area focuses on studying and developing the phase-based features for Voice Liveness Detection. The feature sets are developed using the group delay function which represents the phase variation in the speech signal. In addition, I also have worked on designing a Voice Privacy system using the Linear Prediction method.

I have graduated with my M.Tech. under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India. I completed my B.Tech. in Power System Engineering from University of Petroleum and Energy Studies, Dehradun, Uttarakhand, India.

My research area focuses on the classification of impaired speech, specifically Dysarthria, into several Severity-levels using Deep Learning techniques. In addition, I have also worked on Voice Liveness Detection systems for the improvement of accuracy and reliability of Automatic Speaker Verification (ASV) systems.

I have graduated with my M.Tech. under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India. I completed my B.E. in Electronics Engineering from BVM Engineering College, Vallabh Vidhyanagar, Gujarat, India.

My research area focuses on designing a voice privacy system which anonymizes the speaker specific information residing in the spoken utterance without affecting it’s naturalness and intelligibility. In addition, I also have worked on Replay Spoof detection for voice assistants.

I have graduated with my M.Tech. under the supervision of Prof. Hemant A. Patil and Dr. Hardik B. Sailor from Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India. I completed my B.E. in Electrical and Electronics Engineering from Lakshmi Narain College of Technology, Indore, Madhya Pradesh, India.

My research area focuses on improving the performance of children’s ASR using various speech processing techniques and deep learning architectures. In addition, I also worked to improve the performance of the far-field and short-duration speaker verification system by developing the feature cues that are more robust to noise and capture the global information of the speech.

Ms. Mirali Purohit was a master student at Speech Research Lab, DA-IICT from January 2019 to July 2020. Her research work is to solve Speech Pathology tasks, such as severity-based classification, binary classification, making impaired or whispered speech more intelligible, etc. using Deep Learning (DL)-based methods. Google Scholar

I have done a summer research project and a mini B.Tech project during my undergraduate studies under the supervision of Prof. Hemant A. Patil from Dhirubhai Ambani Institute of Information and Communication Technology, Gandhinagar, Gujarat, India. My research area focuses on applying the ‘Attention’ architecture, which has mainly been useful for Natural Language Processing, to different types of speech data and analyzing its performance.