Multimodal interaction means using different ways to communicate with a computer or device, like by talking or touching a screen. Just like when you talk to your friends, you use your voice and your body language to express your ideas and feelings. Similarly, when we interact with a device, we use different ways to communicate with it.
For example, you can talk to your phone to ask for directions or to play music, or you can swipe and tap the screen to open apps or select different options. In multimodal interaction, you can use more than one way to communicate with a device at the same time, like using your voice and gestures to play a game on a tablet.
Multimodal interaction makes it easier to use devices because you can choose the way that feels most natural for you. It also makes it possible to create more accessible devices for people who may have difficulty using just one mode of interaction, like those who are visually impaired and cannot see the screen, but can use voice commands or touch input.