Profile Links:
Embedded Files
Hello ! I am Dr. Sandipan Dhar (Ph.D.)
I am currently working as a European Research Consortium for Informatics and Mathematics (ERCIM) Postdoctoral Fellow at Fraunhofer IIS, Erlangen, Germany. Prior to this, I have worked as an Institute Postdoctoral Fellow at the Digital Audio Processing Lab, Indian Institute of Technology (IIT) Bombay, India. In addition to that, I also have had the opportunity to work with several other academic and industrial research labs as a researcher, including Educational Technology Laboratory of Norwegian University of Science and Technology (NTNU Norway), Sony Research India Bangalore, Audio-Labs of Fraunhofer & Friedrich-Alexander University (FAU) Erlangen-Nürnberg, etc.
I have pursued my PhD from the Department of Computer Science and Engineering (CSE), National Institute of Technology Durgapur (NIT-DGP), West Bengal, India (2019–2024). My doctoral research work was focused on Speech Synthesis using Generative Adversarial Network (GAN) models. I have completed my M.Tech in CSE from NIT-DGP (2017–2019) and B.Tech from Jorhat Engineering College (a state government engineering college in Assam, India) (2012–2016).
I have deep interest in several areas of applied AI research, including voice conversion, text-to-speech synthesis (TTS), singing voice synthesis, speaker identification and verification, speech command recognition, speaker anonymization, neural audio codec, speech enhancement, neural architecture search, medical image analysis, and AI in agriculture.
I am also the co-initiator of the Soft Computing and Machine Learning Group (SCML Group): https://www.linkedin.com/company/scml-group. Several of my recent research works have been published in esteemed international journals and conferences such as IEEE TNNLS, IEEE TAI, Interspeech, ICASSP, EAAI, APSIPA, IJCCI, SPECOM, and others.
Apart from research, I have a deep interest in music, literature, painting, and karate (martial arts).
Resume link: https://shorturl.at/8evQx
Ph.D. Thesis link: https://tinyurl.com/yycn4b48
Total Publications (Journals, Conferences, Book Chapters): 22
Citation score: 255 H-index: 9 i10-index: 9
Contact Details:
Mail-id: sandipandhartsk03@gmail.com
Phone: +91-8638940660, +91-8876816368 (WhatsApp)
Postdoc Experience
Fraunhofer IIS Erlangen (Germany)
Institute: Fraunhofer IIS
Duration: Dec 2025 - Dec 2026
Supervisor: Dr. Christian Dittmar (Group Manager, Spoken Language Processing Team, AudioLabs)
Domain of research: Neural Speech Coding, Text-to-Speech Synthesis, Voice Conversion
Fellowship: European Research Consortium for Informatics and Mathematics (ERCIM) Postdoctoral Fellowship
Indian Institute of Technology Bombay (IIT-B)
Department: Department of Electrical Engineering (EE Dept.)
Duration: Dec 2024 - Nov 2025
Supervisor: Prof. (Dr.) Preeti Rao (Professor at the EE Dept, IIT-B)
Domain of research: Singing Voice Synthesis, Speaker Anonymization, Text-to-Speech Synthesis
Fellowship: IIT-Bombay Institute Postdoctoral Fellowship
Education Details (Ph.D., M.Tech, B.E)
With my Ph.D. supervisor Dr. Nanda Dulal Jana Sir (first from right), Assistant Prof of NIT Durgapur, CSE Dept, and co-supervisor Prof. (Dr.) Swagatam Das Sir (first from left), Professor and former HOD of ISI Kolkata, ECS-Unit
Ph.D.
Ph.D.
PhD: Computer Science and Engineering (CSE), National Institute of Technology (NIT) Durgapur, India (Institute of National Importance)
PhD supervisors: Dr. Nanda Dulal Jana (Assistant Prof of NIT Durgapur, CSE Dept) and Prof. (Dr.) Swagatam Das (Professor and former HOD of Indian Statistical Institute Kolkata, Electronics and Communication Sciences Unit).
Batch: 2019-2024
Domain of research : Speech Synthesis Using Deep Generative Models.
UGC-NET-2019 and GATE-2017 Qualified
Received NIT-Durgapur Institute Ph.D. Fellowship (2019-2024)
With my M.Tech project supervisor Prof. (Dr.) Gautam Sanyal Sir (Retired Professor and former HOD of NIT Durgapur CSE Dept)
M.Tech
M.Tech : Computer Science and Engineering (CSE), NIT Durgapur, India (Institute of National Importance)
Batch: 2017-2019
M.Tech final year thesis : Aesthetic Analysis of Images Containing Human Faces Using Deeplearning Approaches.
Final year project guide : Prof. (Dr.) Gautam Sanyal. (Retired professor and former HOD of NIT Durgapur CSE Dept)
Received GATE Scholarship (2017-2019)
JEC B.Tech CSE Batch of 2012-2016
B.E
B.E/B.Tech : Computer Science and Engineering (CSE), Jorhat Engineering College (JEC) (State Government Engineering College of Assam, India)
Batch: 2012-2016
Schooling
Class 12: Tinsukia College, (Assam, India) Science Stream. (Year:2010-2012)
Class 10: Tinsukia Railway High School (Assam, India). (Year: 2000-2010)
Academic Institutions and R&D Labs I Have Worked With as a Researcher (From M.Tech to Postdoc)
Experience
Working as a European Research Consortium for Informatics and Mathematics (ERCIM) Postdoctoral Fellow at Fraunhofer IIS, Erlangen, Germany from Dec, 1, 2025.
Worked as an Institute Postdoctoral Fellow (IPDF) at the Digital Audio Processing (DAP) Lab of the Indian Institute of Technology Bombay (IIT-B) Electrical Engineering Department (From Dec 23, 2024) under the supervision of Prof. (Dr.) Preeti Rao. (https://shorturl.at/Gb1Vn) (https://hosturl.link/HkqhNM)
Speech Generation Research Intern at the Sony Research India: Sony Research & Development (April 15, 2024 - Dec 20, 2024) . (https://shorturl.at/LXLcj)
Lead Research Project Coordinator of a consultancy project titled "Development of AI Based Voice to Voice Synthesis", sponsored by Stone Media (Mumbai) in collaboration with NIT-DGP (Dr. Nanda Dulal Jana's Lab, CSE Dept) (March 1, 2024 - Aug 14, 2024). (https://shorturl.at/xUDUl)
Co-initiator of the Soft Computing and Machine Learning Group (SCML Group: https://www.linkedin.com/company/scml-group) since 2019 (Aug).
Recent Achievements
Delivered a talk on the Fundamentals of AI at Dayanand Sagar College of Engineering, Bengalore, India.
Delivered a talk on the Foundations of Speech Synthesis, Organized by KIIT, Odisha, India.
Served as a Workshop Organizer for the EMNLP 2026 workshop IMPACT-SPEECH 2026.
Received invitation to give a talk on "A Journey into Generative Speech Technologies: Foundations to Frontiers" in the Winter School on Deep Learning (WSDL) 2025 organized by ISI-Kolkata.
Recipient of the ERCIM Alain Bensoussan Postdoctoral Fellowship 2025 (link: https://fellowship.ercim.eu/)
Received invitation to deliver a talk on "The Rise of Generative AI: Redefining Image, Speech, and Music" by Sikim Manipal Institute of Technology (SMIT), India, 2025.
Received Invitation to deliver a speech on "Speech Synthesis Reimagined: AI Models Mimicking Natural Human Speech" at SOA Deemed to be University, Bhubaneswar, Odisha, India
Received the best Ph.D. thesis award (6th Universal Innovators Leadership Awards 2025) at the 8th International Conference on Innovative Computing and Communication (ICICC) 2025 held in Delhi.
Received invitation to deliver a talk on "Recent Advancements in Speech Synthesis Technology" organized by Sikim Manipal Institute of Technology (SMIT), India, 2025.
Page updated
Google Sites
Report abuse