Text to speech synthesis systems in Indian languages
IIT Madras has been working on building text to speech synthesis (TTS) systems since 2004 with funding from IBM and MeiTY. Initial efforts were on building small footprint TTS systems in the unit selection framework. Since 2009, IIT Madras has led a consortium of Institutions for building TTS systems in multiple Indian languages.
About Indic TTS
This is a project on developing text-to-speech (TTS) synthesis systems for Indian languages, improving quality of synthesis, as well as small foot print TTS integrated with disability aids and various other applications. This is a consortium based project funded by the Ministry of Electronics & Information Technology (MeiTY), Government of India involving 23 institutions and SMT, IITM being one of them.
.1e11269f.png&w=2048&q=75)
Database
A special corpus of Indian languages covering 13 major languages of India.
Common Label Set
Listing and mapping phonemes of 13 Indian languages, unifying sounds under one label for clarity
Unified Parser
This parser attempts to unify the languages based on the Common Label Set.
Segmentation
Crucial phoneme segmentation in speech synthesis, explicitly implemented.
Voices
Distribution of synthetic voices in 13 Indian languages, a collaborative effort by partners.
Documentation
The documentation contains Hybrid Segmentation for segmenting speech
Empowering Inclusivity
TTS Challenges Organised
CSTR Edinburgh organises the Blizzard Challenge every year. Blizzard Challenge in 2014-15 for building TTS systems in Indian languages was organised.The data for the challenge (both train and test sets) were designed and developed by IIT Madras. As part of the NLTM-pilot project (2021-2022), a TTS challenge was organised by CDAC Mumbai
Text-to-Speech Synthesis for Indian Languages in Digital Accessibility and Education
By enabling text-to-speech synthesis for Indian languages, the project aims to enhance accessibility for individuals with visual impairments, promote literacy, and facilitate the dissemination of information in regional languages across digital platforms. Additionally, the TTS systems can find applications in e-learning, automated customer support, and multilingual communication, thereby fostering inclusivity and linguistic diversity in the digital space.
The project envisions the continual expansion of the TTS systems to encompass a broader spectrum of Indian languages and dialects, thereby promoting inclusivity and accessibility for all. We collaborate with educational institutions, nonprofit organizations, and government agencies to integrate these TTS systems into various initiatives aimed at enhancing digital literacy, language preservation in India.
Indic TTS
Indic TTS : Enhancing text-to-speech (TTS) synthesis for Indian languages, optimizing quality and integrating compact TTS into disability aids and diverse applications.
Home
About
People
Publications
Demo
Contact Us
© Copyright 2023, Speech Technology Consortium,
Bhashini, MeiTY and by Hema A Murthy & S Umesh,
Department Of Computer Science and Engineering and Electrical Engineering, IIT MADRAS. All Rights Reserved
Maintained by NetPhenix IT Solutions.