MERaLiON: Multimodal Empathetic Reasoning and Learning in One Network
Human-Centric AI for Southeast Asian Speech and Beyond
MERaLiON builds on A*STAR’s expertise in multimodal AI and speech processing to create a large language model that captures Southeast Asian communication styles. Its architectures capture not only words but also tone, pitch and environmental sounds, tuned to regional patterns such as code switching, local expressions and culturally nuanced emotional cues.
Unlike conventional systems that convert audio into text, MERaLiON processes speech directly, preserving signals such as speaker identity and emotion that are often lost in traditional pipelines. This results in more accurate and natural interactions, with applications across speech translation, call centre analytics, accessibility tools and AI wellness assistants.
Part of Singapore’s $70M National Multimodal Large Language Model Programme, MERaLiON is open source and backed by partners including ST Engineering, Grab, Singtel and Microsoft, driving adoption across the region.
For enquiries and collaboration opportunities, please use our contact form.
Safeguarding Online Trust and Safety
Trustworthy AI for the Age of Deepfakes
Deepfaic, a spin-off from A*STAR, is applying its extensive research in multimodal AI to tackle the risks of manipulated digital content. Its platform, trained on over seven million examples, detects deepfakes across video, audio, images, and text with real-time accuracy. The system integrates seamlessly into enterprise workflows, supporting secure video interviews, Know Your Customer checks, and online communications. It helps organisations protect against impersonation, fraud, and disinformation, while enabling publishers to validate the authenticity of media content.
Supported by the Centre for Advanced Technologies for Online Safety, Deepfaic is advancing trusted AI tools from research into industry. Its API-ready platform is already being tested in pilots with major enterprises, demonstrating its value in safeguarding identity, brands, and public discourse in an increasingly AI-driven world.
For enquiries and collaboration opportunities, please use our contact form.
