DDL keywords

The availability of an increasing number of multimedia documents makes it necessary to develop efficient tools for automatic document indexing and mining. As for audio documents, it is indispensable that information be extracted automatically from the signal in order, for example, to allow indexing by search engines.

The aim of automatic speaker identification is to determine the identity of a speaker from a recorded utterance, or to verify a proposed identity for a given utterance, i.e., accepting or rejecting it.