SUKHSANDESH: An Avatar Therapeutic Question Answering Platform for Sexual Education in Rural India

TL;DR

The paper tackles the limited and stigmatized access to sexual education in rural India by proposing SUKHSANDESH, an avatar-based, multi-stage QA platform that combines retrieval and generative AI with an empathetic talking-head avatar. It leverages the KAB dataset and Hindi audio inputs, enabling regional-language delivery and real-time audio-visual responses to educate adolescents while prioritizing safety through guardrails and data sanitisation. The approach includes a deployment plan with Gram Vaani, supports incremental learning and scalability, and targets SDGs related to health, education, and equality. If successful, it could substantially improve accessibility, trust, and engagement in sexual health education for rural Indian populations, with implications for public health and social development.

Abstract

Sexual education aims to foster a healthy lifestyle in terms of emotional, mental and social well-being. In countries like India, where adolescents form the largest demographic group, they face significant vulnerabilities concerning sexual health. Unfortunately, sexual education is often stigmatized, creating barriers to providing essential counseling and information to this at-risk population. Consequently, issues such as early pregnancy, unsafe abortions, sexually transmitted infections, and sexual violence become prevalent. Our current proposal aims to provide a safe and trustworthy platform for sexual education to the vulnerable rural Indian population, thereby fostering the healthy and overall growth of the nation. In this regard, we strive towards designing SUKHSANDESH, a multi-staged AI-based Question Answering platform for sexual education tailored to rural India, adhering to safety guardrails and regional language support. By utilizing information retrieval techniques and large language models, SUKHSANDESH will deliver effective responses to user queries. We also propose to anonymise the dataset to mitigate safety measures and set AI guardrails against any harmful or unwanted response generation. Moreover, an innovative feature of our proposal involves integrating ``avatar therapy'' with SUKHSANDESH. This feature will convert AI-generated responses into real-time audio delivered by an animated avatar speaking regional Indian languages. This approach aims to foster empathy and connection, which is particularly beneficial for individuals with limited literacy skills. Partnering with Gram Vaani, an industry leader, we will deploy SUKHSANDESH to address sexual education needs in rural India.

Figures (1)

• Figure 1: A schematic diagram of SukhSandesh, our proposed multi-staged QA system for sexual education. SukhSandesh consists of three stages, namely, the input phase, the QA phase and the output phase. Initially, it takes the user’s audio query in a regional language, i.e., Hindi, as input. The Hindi audio query is translated to English via the audio-to-text translator API of Bhasini. The text query is then fed into the QA modules. The QA module comprises retrieval-based and LLM-based modules. The retrieval-based module retrieves the most relevant QA pair with the query, and the corresponding answer is returned. If a relevant pair is not found based on the relevance score, LLMs will generate responses with AI guardrails over the query prompt to regularise safety. Finally, the text response is converted to real-time audio-visual representation with emotion using a talking head empathetic avatar. It is to be noted that since the output audio is in Hindi, we aim to finetune the existing talking head avatars using Hindi video data.