Anusha Prakash recently graduated as a PhD Scholar from the Electrical Engineering department at the Indian Institute of Technology (IIT) Madras, India. Her research focused on developing high-quality text-to-speech (TTS) synthesizers for Indian languages, with a particular emphasis on low-resource languages in a multilingual context. She has extensive experience working with various TTS frameworks, ranging from traditional techniques like unit selection synthesis, HMM-based methods, and conventional neural networks to state-of-the-art end-to-end speech synthesizers. Her work integrates linguistic knowledge and signal processing techniques with deep learning methods to enhance synthesis quality and intelligibility. Additionally, she has contributed to improving the quality of dysarthric speech.
Anusha has been involved in various government-funded projects. Most recently, she served as a Principal Project Officer in a project titled “Speech Technologies for Indian Languages,” which is part of the “National Language Translation Mission (NLTM)-Bhashini.” The primary goal of this project is to translate technical lectures in English into various Indian languages. She has trained TTS systems for 15 Indian languages, including Assamese, Bengali, Bodo, Gujarati, Hindi, Kannada, Malayalam, Manipuri, Marathi, Odia, Punjabi, Rajasthani, Tamil, Telugu, and Urdu, as well as Indian English with different accents. Some of these models have been deployed as part of the project and have been integrated with other applications, such as speech-to-speech and video-to-video transcreations.
- Doctor of Philosophy (PhD), Developing end-to-end text-to-speech synthesis systems for Indian languages, Indian Institute of Technology Madras, 2017 - 2024
- Master of Science (MS) by Research, Cross-lingual Speech Synthesis and Enhancement of Dysarthric Speech, Indian Institute of Technology Madras, 2013 - 2016
- Bachelor of Engineering (B.E.), Electrical and Electronics Engineering, RNS Institute of Technology, Bengaluru, 2008 - 2012
- Principal Project Officer @ ICSR, IIT Madras - [Jul 2022 - Mar 2023]
- Speech Technologies in Indian Languages (as part of Bhashini- National Language Translation Mission), funded by the Ministry of Electronic & Information Technology (Meity), Govt. of India.
- Teaching Assistant @ Indian Institute of Technology Madras - [Jul 2017 - Jun 2022]
- Teaching Assistant for different courses (Speech Signal Processing (post-graduate level), Signals & Systems (under-graduate level), Digital Signal Processing (under-graduate and post-graduate levels)) in the Department of Electrical Engineering, including being Head TA (Jan - May 2019).
- Project Staff (part-time) @ ICSR, IIT Madras - [Apr 2020 - Jun 2022]
- Speech Technologies in Indian Languages - [Apr 2022 - Jun 2022]
- As part of Bhashini- National Language Translation Mission, funded by the Ministry of Electronic & Information Technology (Meity), Govt. of India.
- Automatic Speech Recognition in Indian English, Tamil, Hindi, and Text to Speech Synthesis for conversational speech in Indian languages - [Apr 2020 - Mar 2022]
- As part of National Language Translation Mission Pilot, funded by the Ministry of Electronic & Information Technology (Meity), Govt. of India.
- Speech to Speech Machine Translation - [Apr 2020 - Mar 2022]
- Funded by the Office of the Principal Scientific Adviser (PSA), Govt. of India.
- Text to Speech Generation with chosen accent and noise profile for Aerospace and Industrial domains - [Apr 2020 - Feb 2021]
- Funded by the Department of Science and Technology (DST), Govt. of India.
- Speech Technologies in Indian Languages - [Apr 2022 - Jun 2022]
- Project Officer @ ICSR, IIT Madras - [Jun 2014 - Jun 2017]
- Development of Text to Speech systems for Indian languages, funded by the Department of Information Technology, Govt. of India
- Project Officer @ ICSR, IIT Madras - [Jul 2012 - Mat 2014]
- Development of Text to Speech systems for Indian languages, funded by the Department of Information Technology, Govt. of India
- Programming Languages: C, C++, Python, Perl
- Deep Learning Tools: PyTorch, Merlin, ESPNet
- Other Tools/Libraries: MATLAB, LaTeX, Festival, HTS, HTK, Kaldi
- Text-to-Speech (TTS) system development and deployment for 15 Indian languages
- Speech singal processing
- Deep learning models for speech
- Accepted to the ICASSP Rising Stars in Signal Processing Workshop, 2023, and presented thesis work on "Developing End-to-End Speech Synthesis Systems for Indian Languages".
- Accepted to the Doctoral Consortium Workshop, INTERSPEECH, 2019, and presented work on "End-to-End Speech Synthesis for Indian Languages".
- Received Gold Medal for the Highest Scorer of the batch 2008-2012 in the Electrical and Electronics Engineering department, RNS Institute of Technology, Bangalore, India.