Language, images, sound
Speech, images, video and multimodal systems are not all the same technology.
The chapter at a glance
TextImages and videoSpeech and sound
Multimodal model
Understanding or creating
Checking the source
From “Images and video” it loops back to “Multimodal model”.
In this chapter
- 1How does AI work with language?Natural language processing (NLP) covers translation, classification, working out meaning and generating text.
- 2What does a computer “see” in a picture?Computer vision treats images and video as data in which it looks for objects, patterns or movement.
- 3Speech recognition and generating soundAI can turn speech into text, generate a voice or recognise particular sounds.
- 4How does AI create images?Generative image models create pictures from text, images or other inputs.
- 5How does AI create video?A video model has to create or change many connected images over time.
- 6What does multimodal AI mean?A multimodal model can handle several kinds of data: for example text, images, sound or video.