Software Called Capable of Copying Any Human Voice

From: Matthew Gaylor (
Date: Mon Aug 06 2001 - 14:42:41 MDT

[Note from Matthew Gaylor: People may end up looking like Borg as
even I'd consider installing a digital signature device on my larynx.]

"Software Called Capable of Copying Any Human Voice"

Permanent link to this news article:

Software Called Capable of Copying Any Human Voice

New York Times, July 31, 2001

Voice cloning software -- replicating a person's voice so perfectly
that the human ear cannot tell the difference -- has been developed
by AT&T.

The text-to-speech software, called Natural Voices, allows for
recordings of a person's voice to utter things that the person never
actually said.

The advances raise several sticky issues. Who, for example, owns the
rights to a celebrity's voice? Will synthesized voices compete with
those of live actors? Could synthesized voices eventually be capable
of tricking people into thinking that they were getting phone calls
or digital audio recordings from people they know?

To build the software that recreates unique voices, engineers record
up to 40 hours of readings.

Other companies and research centers, like I.B.M. Research and
Lernout & Hauspie Speech Products, are also experimenting with this
technique - which is called concatenative speech synthesis - to
improve the quality of text-to-speech software.


Subscribe to Freematt's Alerts: Pro-Individual Rights Issues
Send a blank message to: with the words subscribe FA
on the subject line. List is private and moderated (7-30 messages per week)
Matthew Gaylor, (614) 313-5722 ICQ: 106212065 Archived at

This archive was generated by hypermail 2b30 : Fri Oct 12 2001 - 14:40:03 MDT