Automatic Speech Recognition and Understanding

Dion speechHuge amounts of audiovisual media are generated on a daily basis: parliamentary session, private meetings, TV and radio shows, public speeches, medical recordings, and many more. The magnitude of such quantity of information makes it impossible to be managed efficiently solely by human intervention. Automatic Speech Recognition and Understanding (ASRU) comes in handy when managing and indexing automatically such large amounts of audiovisual content.

In addition, speech is the most natural way of communication. However, computer interfaces are typically a keyboard and a mouse, or more recently, touch screen interfaces, which are often an inadequate way of input. Here, ASRU plays an interesting role for building human-computer interfaces.

The speech utterances are decoded into strings of words or into strings of semantic units. Finite-state grammars are used as the basis of such systems. These finite-state grammars are learned automatically from real examples of utterances or text. Applications: telephone exchange services, device control by voice, information queries, etc.