Talk in ISL: Empowering the Deaf Community in India

Bridging the Gap

India is home to nearly 63 million deaf individuals, as noted in a Wikipedia article. Alarmingly, only 26.1% of the 15 million deaf individuals of working age are employed. This low employment rate can be attributed to two main factors: a lack of education within the deaf community and their inherent challenges in effective communication. Providing access to technology that can help them engage with society, be more productive, and realize their potential could significantly improve their quality of life.

Research in Sign Languages

Sign languages, such as American Sign Language (ASL), Chinese Sign Language (CSL), and British Sign Language (BSL), have been subjects of research for quite some time. Consequently, sign languages have gained acceptance as bona fide natural languages. Being a visual medium, sign language lends itself well to machine learning-based solutions. Various research organizations, universities, and startups are working in the domains of education and communication using sign languages.

Efforts in India

In India, the Indian Sign Language Research and Training Centre (ISLRTC) focuses on research and training in Indian Sign Language (ISL). The Noida Deaf Society, another notable NGO, works on ISL training and making deaf individuals economically productive. Several other organizations are also producing content in ISL to benefit the deaf community.

The Talk in ISL (TIISL) Project

One of the pioneering projects by the Longtail AI Foundation (LAF) is to address the communication and education challenges faced by the deaf community in India. The Talk in ISL (TIISL) project aims to facilitate meaningful communication between deaf and hearing individuals.

Data is the cornerstone of machine learning-based solutions. Hence, amassing a substantial amount of ISL content is crucial for training models and ensuring their output is reliable. The immediate goal of the TIISL project is to gather a comprehensive ISL dataset. Additionally, we are developing technology to generate synthetic data to augment this dataset. Achieving a large dataset would mark a significant milestone in ML-based ISL research, positioning it alongside mature datasets like BOBSL, CSL-Daily, and Phoenix14T.

Core Principles of the TIISL Project

1. Openness:

LAF’s principles ensure that the ISL dataset and the technology built upon it will be accessible to researchers and individuals aiming to improve their daily lives and opportunities.

2. Responsibility:

The technology developed will responsibly facilitate communication between deaf and hearing individuals. This responsibility requires ongoing improvements in AI model development.

3. Quality:

Being open and free does not compromise quality. On the contrary, the commitment to responsibility necessitates that the service quality matches that of any paid service.

By focusing on these principles, the TIISL project aims to revolutionize communication and education for the deaf community in India, fostering inclusivity and empowerment.

We are always seeking ML researchers to join us in achieving our goals. Click here to contact us.