This is very helpful for speaker identification and overlapping conversation.
From the en.wikipedia.org
Text-independent systems are most often used for speaker identification as they require very little if any cooperation by the speaker.
From the en.wikipedia.org
The figure of 422 million specifically includes all such people, whereas the figure of 258 depends on speaker identification as recorded in the census.
From the en.wikipedia.org
Identification is the common ground that exists between the speaker and audience.