Pranaw Kumar

Introduction

Pranaw Kumar is currently working as a Scientist 'E' /Joint Director at the Centre for Development of Advanced Computing (C-DAC), Mumbai. He has been associated with CDAC Mumbai for the last 16 years. His research interests include language and speech technologies. He works for Text-to-Speech Synthesis System (TTS), Automatic Speech Recognition (ASR) system for Indian Languages, and related applications. He has been involved in the development of Marathi, Odia, and Indian English TTS Systems, Hindi, Marathi, Odia, and English ASR Systems, and various applications like TTS browser plugin, SMS Reader, TTS building Toolkit (TBT), Framework to integrate TTS system into websites, Speech Enabled IVRS System, Speech Enabled Multilingual chatbot, Speech Enabled Examination System for Visually Impaired Persons, etc. Currently he is Principal Investigator of a consortium based sub project 'Speech technologies in Indian languages' under the Project titled 'National Language Translation Mission (NLTM) : BHASHINI' for Mumbai centre. He was Principal Investigator of following two projects for Mumbai Centre:

Natural Language Translation Mission - Automatic Speech Recognition in Indian English, Tamil, Hindi, and Text to Speech Synthesis for conversational speech in Indian languages
Integration of 13 Indian Language TTS Systems with screen-readers for Windows, Linux, and Android platforms

Professional Experience

Joint Director / Scientist 'E', C-DAC Mumbai (January 2022 - Present)
Principal Technical Officer, C-DAC Mumbai (January 2018 - December 2021)
Senior Technical Officer, C-DAC Mumbai (Feb 2014 - December 2017)
Staff Scientist, CDAC Mumbai (August 2008 - Feb 2014)
Project Engineer, CDAC Mumbai (December 2007 - August 2008)

Scientist 'E'/Joint Director

Centre for Development of Advanced Computing (CDAC)

Mumbai, India

pranaw [at] cdac [dot] in, erpranaw [at] gmail [dot] com

Publications

A . Singh et al., "LIMMITS'24: Multi-Speaker, Multi-Lingual INDIC TTS With Voice Cloning", IEEE Open Journal of Signal Processing, 2025, Volume: 6, Pages: 292-302
A . Singh et al., "Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech", IEEE Open Journal of Signal Processing, 2024, Volume: 5, Pages: 790-798
A. Singh et al., "Multi-speaker, Multi-lingual Indic TTS with voice cloning", ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Seoul, Koria, 2024
A. Singh et al., "Lightweight, Multi-Speaker, Multi-Lingual Indic Text-to-Speech," ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-2, doi: 10.1109/ICASSP49357.2023.10433926.
Snehal Chandulal Bajaj, Kamal Kant, Amol V Bole, Pranaw Kumar “Large Vocabulary Continuous Speech Recognition System for Marathi”, International Conference on Advances in Electronics, Communication, Computing and intelligent information systems (ICAECIS-2023)
Atish Ghone et.al. “Automatic Pause Boundary and Pause Duration Detection for Text-to Speech Synthesis System in Indian Languages” ICON 2018, 15 to 18 Decmeber 2018, Punjabi University, Patiyala, Punjab, India
Atish Ghone et.al. “TBT (Toolkit to Build TTS): A High Performance Framework to build Multiple Language HTS Voice” INTERSPEECH 2017: Show & Tell , August 20–24, 2017, Stockholm, Sweden.
Pranaw Kumar, et al. “Seamless Integration of Common Framework Indian Language TTSes in Various Applications” Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) International Conference, IEEE Xplore, page 1-6, 2013
Hemant A Patil, et al. “A syllable-based framework for unit selection synthesis in 13 Indian languages.” Oriental COCOSDA held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE) International Conference, IEEE Xplore, page 1-8, 2013
Hema A Murthy, et al. “Building Unit Selection Speech Synthesis in Indian Languages: An Initiative by an Indian Consortium.” Proceedings of COCOSDA, Kathmandu, Nepal, 2010
Aparna R, Sasikumar M, Kamini K, Pranaw K, Onkar P, Narsaiah BCL. "e-Svaasthya – An Open Source HIS for Indian hospitals" , Proceedings of NCOSS-09 – National Conference on Open Source Software, Navi Mumbai, India, May 25-26, 2009

Challenges/Workshops Organised

LIMMITS'25

Multilingual streaming TTS with neural codecs for Indian languages in ICASSP 2025 (Scheduled)

Summer School on Speech Signal Processing (S4P) 2024

Workshop on Automatic Speech Recognition, as part of summer school activities at Speech Research Lab, DA-IICT, Gandhinagar.

LIMMITS’24
Multi-speaker, Multi-lingual Indic TTS with VOICE CLONING, as part of signal processing grand challenge in ICASSP 2024. (Results Declared)
LIMMITS’23
Multi-speaker, Multi-lingual Indic TTS challenge, as part of signal processing grand challenge in ICASSP 2023. (Results Declared)
Lip-Sync Challenge 2021

A challenge for the "Lip-Syncing in Speech-to-Speech Translation", as a part of the National Language Translation Mission Project funded by MeitY, Govt of India (Results Declared)

Indian Language TTS Development Challenge, 2020

A challenge for the "Development of Text to Speech Synthesis (TTS) for Hindi and Tamil", as a part of the National Language Translation Mission Project funded by MeitY, Govt of India (Results Declared)

Major Sponsored R&D Projects

'Speech technologies in Indian languages' a consortium based sub project under the Project titled 'National Language Translation Mission (NLTM) : BHASHINI', Total Budget:Rs 55.65 Crores (CDAC Mumbai Share:1.77 Crore), Duration : 1st April 2022 to 31st March 2025; Sponsor : MEITY, India.
" ECGC ERP Revamp Project", Total Budget: 110 Crore, Duration: July 2019 to June 2026, Sponsor: ECGC Ltd
“Natural Language Translation Mission - Automatic Speech Recognition in Indian English, Tamil, Hindi, and Text to Speech Synthesis for conversational speech in Indian languages”, CDAC Mumbai Share:15 Lacs, Duration : April’2020-Dec-2021; Sponsor : MEITY, India.
“Integration of 13 Indian Language TTS Systems with screen-readers for Windows, Linux, and Android platforms”, Total Budget:60 Lacs (CDAC Mumbai Share: 27.5 Lacs) , Duration : April’2018-Sept 2019; Sponsor : MEITY, India.
“Citizen Contact Centre – Sampark”, Total Budget:24 Crores , Duration : April’2012-Sept 2016; Sponsor : MEITY, India.
“Development of TEXT to SPEECH SYSTEM in Indian Languages: PhaseII” (A twelve institute consortium effort) Total : 12.66 crores (CDAC Mumbai share: 1.09 crores); Duration : April’2012-Sept 2016; Sponsor : MEITY, India.
"Development of TEXT to SPEECH SYSTEM in Indian Languages” (A five institute consortium effort) Phase I, (CDAC Mumbai share: 40 lacs);March 2009 to Dec 2011

Summary of Research Output

Development of Speech Enabled Examination system for Visually Challenges Students
Development of Speech Enabled Multilingual Chat bot
Development of Framework to integrate Speach Enabled Chat Facility into the website
Development of Toolkit to build Indian Language TTS systems
Development of Framework to integrate Indian Language TTS systems into website
Development of Semi-automatic Voice Response System, Speech Enabled Chat bot, Speech based phone dialing system etc
Development of Hindi and English ASR System
Development of Indian Language TTS Browser Plugin for Firefox and Google Chrome
Development of Indian Language SMS Reader
Development of Text to Speech System for Marathi and Odia

Education

MBA (Marketing Management)

Welingkar Institute of Management, Mumbai

B.E. (Computer Science & Engineering)

Maulana Azad College of Engineering & Technology, Patna, Bihar