As social media platforms become a big part of our lives, it also has a direct impact on our emotions. How often have we been left distressed or demoralised because of some hate or abusive content we have come across on various platforms?

At ShareChat and Moj, we believe our users and creators can grow exponentially when provided with a safe space to express their feelings. We firmly believe ShareChat is for all and it’s our mission to keep it clean, safe and abuse free. As we strive to give our users the best experience, we are pleased to announce that our work "Multilingual and Multimodal Abuse Detection" on detection of abusive behaviour in spoken audio has been accepted at Interspeech 2022!

We would like to congratulate all the authors - Vikram Gupta, Rini Sharon, Heet Shah and Debdoot Mukherjee - for their inspiring efforts.

Abuse detection has been and continues to be a widely explored topic in the textual domain but the same aspect in audio abuse detection still leaves a lot to be desired. In this paper, our authors worked on abuse detection in conversational audio from a multimodal perspective in a multilingual social media setting.