DailyDirt: Computers Talking Back
from the urls-we-dig-up dept
We’ve covered the uncanny valley of various visual works before, but it’s interesting that synthetic speech doesn’t seem quite as polished as digital photo and video editing. Apple’s Siri might be able to respond with some pretty witty comebacks, but everyone can still tell that the voice is computer generated. Here are a few interesting links on artificially-generated sounds and voices.
- AutoTune is so last century — bringing back voices from the dead is the new zombie world order. Vocaloid researchers have developed software that can re-create a person’s singing voice without recordings of the person singing every syllable possible. [url]
- Audio editing software is becoming more like Photoshop — and pretty soon everyone will be able to create podcasts that sound like NPR. This kind of software has been around for a while, but it’s getting more sophisticated and has more tools for extracting and refining voices and sound effects. [url]
- Stephen Hawking’s voice is in need of some new maintenance and upgrades, but apparently the company that made the hardware for his voice synthesizer went out of business. Hmm. How was Hawking’s rap persona created? [url]
- To discover more interesting tech-related content, check out what’s currently floating around the StumbleUpon universe. [url]
By the way, StumbleUpon can recommend some good Techdirt articles, too.
Filed Under: audio editing, autotune, photoshop, software, stephen hawking, synthetic speech, voices
Comments on “DailyDirt: Computers Talking Back”
Is Stephen Hawking robo voice actually his voice?
I’ve always wondered if the voice that Hawkings uses is based on his actual real voice in some way…
Re: Is Stephen Hawking robo voice actually his voice?
Also: in one of his books, he complains that the synthetic voice has an American accent, but since he’s had the robot voice longer than his real voice, he’s gotten used to it by now.
Spectral editing now we are talking 🙂
Finally something better than:
steinberg – WaveLab
WaveLab (Math software)
MAGIX – Sequoia
Algorithmix – reNOVAtor
Algorithmix – easyNOVA
SPEAR (Sinusoidal Partial Editing Analysis and Resynthesis).
Adobe – Soundbooth (ended)
If the software is used to re-create a dead singers voice, who owns the copyright on the voice after it has been re-created? For that matter, I wonder if the software could be used to create new voices which could then be copyrighted, forcing future singers to pay licensing fees to whomever holds the copyright on their voice…
On the topic of computers snapping back at you,.......
You guys may wanna take a look at this:
Laughed my socks off reading this. Peace.