Interesting People mailing list archives

Eerie tech promises to copy anyone’s voice from just 1 minute of audio...


From: "Dave Farber" <dave () farber net>
Date: Mon, 01 May 2017 01:00:52 +0000

---------- Forwarded message ---------
From: the keyboard of geoff goodfellow <geoff () iconia com>
Date: Sun, Apr 30, 2017 at 7:38 PM
Subject: Eerie tech promises to copy anyone’s voice from just 1 minute of
audio...
To:


[would DEARLY LOVE to see this technology used to get, say
https://en.wikipedia.org/wiki/Douglas_Rain's voice -- the voice of The
https://en.wikipedia.org/wiki/HAL_9000 -- onto the iPhone (say, for Siri)
or other voice interaction app type "things"!]

by ABHIMANYU GHOSHAL
https://thenextweb.com/apps/2017/04/24/eerie-tech-promises-promises-to-copy-anyones-voice-from-just-1-minute-of-audio/

I’m not sure how I feel about the upcoming launch of Montreal-based
Lyrebird’s <https://lyrebird.ai/>new service. The company says its API will
let you synthesize speech in anyone’s voice from just a minute-long
recording – which means you could, for instance, generate a clip of
President Trump declaring war on Canada.

Lyrebird has posted some audio examples that sound pretty convincing
(listen below, and find more on this page <https://lyrebird.ai/demo>). The
company says that it doesn’t require the speaker to say the words that
you’ll use the voice to speak in the audio you generate, and it’ll also be
able to create different intonations.

If any of this sounds familiar, it might be because you’re thinking of Adobe’s
demo of its similar tech last November
<https://thenextweb.com/apps/2016/11/04/adobes-upcoming-audio-tool-lets-you-synthesize-speech-in-anyones-voice/#.tnw_S10pICCa>.
But while Adobe’s Project VoCo requires 20 minutes of audio and appears to
use system resources for speech synthesis, Lyrebird only needs a
minute-long recording and says it’s close to launching its cloud-based API
to process audio and spit out results.

As I wrote when we covered Project VoCo last year, it’s likely that such
software will lead to the creation and distribution of plenty of misleading
information that people might believe to be genuine.

On its Ethics page <https://lyrebird.ai/ethics>, Lyrebird says that its
technology “questions the validity of such evidence as it allows to easily
manipulate audio recordings.” It added:

[SNIP]

https://thenextweb.com/apps/2017/04/24/eerie-tech-promises-promises-to-copy-anyones-voice-from-just-1-minute-of-audio/

-- 
Geoff.Goodfellow () iconia com
living as The Truth is True
http://geoff.livejournal.com



-------------------------------------------
Archives: https://www.listbox.com/member/archive/247/=now
RSS Feed: https://www.listbox.com/member/archive/rss/247/18849915-ae8fa580
Modify Your Subscription: https://www.listbox.com/member/?member_id=18849915&id_secret=18849915-aa268125
Unsubscribe Now: 
https://www.listbox.com/unsubscribe/?member_id=18849915&id_secret=18849915-32545cb4&post_id=20170430210110:A8794C4E-2E09-11E7-AA6E-E3EEA3B0F5EE
Powered by Listbox: http://www.listbox.com

Current thread: