sign up for our
NEWSLETTER

Home Shop Subscribe Advertise Articles Directories Classifieds Calendar FAQs Contact Us Login

VOICE ACTING
The Human Voice Trumps Siri's World -
At Least For The Foreseeable Future

March 30, 2016

By Bobbin Beam

Voice Actor

No, the title of this article has nothing to do with a certain political candidate running now for U.S. President. I'm referring to a recent article in Wired about brain researchers who have repeatedly attempted to perfect brain-to-computer interfaces by using various electrode implants and prosthetics.

Researchers at Brown University initially had some success with subjects who could control a robotic arm with the mind using neural brain implants.

As fascinating as the progress was, one researcher, neurosurgeon Phil Kennedy, was more intent on pursuing the more challenging concept of brain-to-computer speech cognition.  

COMPLEXITY OF HUMAN SPEECH


Kennedy knew that human  speech is vastly more complex than robotic arms.

It involves the orchestrations and contractions and releases of more than 100 different muscles, from the diaphragm, face, throat, vocal folds, tongue and lips to be intelligible.

And to fabricate a minimally invasive and compact brain implant electrode that could accurately orchestrate the complexity of vocal language with only a few wires was a huge hurdle.

Kennedy’s research project  eventually ran out of money and the FDA revoked approval of the use of implants.  

STILL, SOME PROGRESS

Still, there has been some progress on brain-to-speech.

For instance, algorithms have been created for prostheses that assist patients with ALS and others who can no longer speak. But the outcomes are not always 100% accurate.  

And of course, software for voice recognition, TTS and Siri speech has been around for decades.

Kennedy says all this helps superficially, but isn’t very useful in the real world. "Siri’s not good enough, " he says.

I’ve heard script to speech synthesizer recordings and agree with Kennedy. We’re a long way away from perfecting artificial intelligence.  

So, what does it all mean to the voice over world? Considering the complexity of human emotions, passion, expressiveness and the myriad of ways one can read a single line, it may take a lot more time to even come close to human vocalization that any app will offer.
------------------------
ABOUT BOBBIN
Bobbin Beam has been a full-time voice over talent and voice actress since 1985, and is currently based near Milwaukee, WI. She's a signature imaging voice of various television and radio stations worldwide. Working mostly "from the trenches” at her broadcast-quality home studio, she voices radio and television commercials, promos, programs, corporate videos, narrations, audiobooks, e-Learning, documentaries, explainer videos, and apps. Her clients include ABC, Disney Parks, Discovery Channel, Mitsubishi, Merck, Toyota, Citgo, Nivea, St. Jude’s Children’s Hospital, Pro Flowers and LA Times.

Email: bobbin@BobbinBeam.com
Web: www.BobbinBeam.com
The Wired article

Your Daily Resource For Voice-Over Success
Tell Us What YOU Think!
Please Note: Since we check for spam, there will be a slight delay in the actual posting of your comment.
Your Name:
Your Email Address (will not be published):
Your Comment:
Your Comment:
Security code:     
Comments (6)
Roy Wells
4/1/2016 at 5:44 PM
Machine translation is like listening to a symphony played in only one key. Very boring.
j.valentino
3/30/2016 at 2:04 PM
Why no mention of Cereproc and other companies who are really nailing it when it comes to text to speech synthesis? Seems article is an attempt to put newbies at ease.

Whole thing could be one line:

Considering the complexity of human emotions, passion, expressiveness and the myriad of ways one can read a single line, it may take a lot more time to even come close to human vocalization that any app will offer.
Joel Richards
3/30/2016 at 12:17 PM
Interesting. Thanks for linking to the Wired article, too. Personally I think we'll start to feel some encroachment within the next few years. Especially as a generation will grow up already accustomed to mechanical TTS voices. However, it will take a long time for TTS and computers to pass over the uncanny valley. Certain types of voice-over require more emotion than information, and those jobs will persist the longest. For those of us planning on being in the field for 20+ more years, I think it worth following the growth of this technology.
Bobbin Beam
3/30/2016 at 11:38 AM
Thanks, Rory.
And Debbie, I didn't know you went to Brown. So that explains your "inner brainiack-ness". :) Glad you enjoyed the info as much as I found it fascinating.
Best,
Bobbin
Debbie Irwin
3/30/2016 at 10:06 AM
Thanks for highlighting this work from my alma mater! Brain research is fascinating and we have a long way to go before we can trick humans into believing that computers are us!
Rory O'Shea
3/30/2016 at 9:32 AM
Excellent piece, Bobbin.
Back to Articles
Get your bi-weekly dose here ... all things VO!
Email alerts to new VoiceOverXtra articles
With Sean Daeley and Paul Stefano - check it out!
Inspiring interviews help your VO career