[News] Lyrebird can 'copy the voice of anyone' in a minute

[StyM]

http://hexus.net/tech/news/software/...anyone-minute/

Montreal-based Lyrebird has published a microsite showcasing its voice imitation algorithms. The AI-startup claims it has developed an API which will let you synthesize speech using anyone's voice - from just a minute-long recording of the person. The speaker doesn't need to say any off the words contained in the audio generated. Furthermore, you will be able to select emotions for the speech, such as anger, sympathy, or stress.

In the main demo from the showcase page at Lyrebird.ai, embedded above, you get to hear a synthesized voice switch between Barack Obama, Donald Trump, and Hillary Clinton imitations. There are plenty of other examples to check over. This is pretty impressive for real-time generation and voice imitation switching, though its easy in some segments to detect the 'robotic' speech sound.

As TNW reminds us, Adobe showcased similar voice mimicking tech last year, under the name of Project VoCo. However, Adobe's tech required about 20 minutes of user speech for its mimicking tasks plus its software package installed on the client system. Lyrebird only needs a minute long recording and will shortly launch a cloud based API service for you to upload audio and download your synthesized speech.

[Sparky]

This intrigues me given this could correlate well into the industry I'm in (speech generation devices for the disabled).

[vario]

This can be terrifying .If its THAT good, any court case involving someones voice on recording can be fake.

[bluestang]

Huh, I was expecting to read something about Parrots

This intrigues me given this could correlate well into the industry I'm in (speech generation devices for the disabled).

Interesting. I was amazed (and disappointed) at the same time with devices available when we had to go through assessment, research and finally insurance denial with our son who has ADHD w/Anxiety and specific learning disabilities. This was about 5-ish or so years ago when he wasn't talking much at 4-5 yrs old and needed something for communication in school and home. It was a device made by Tobii. After everything we had to go through I took matters into my own hands and ended up buying an iPad 2 and a $100 app called Sono Flex for him. That along with lots of speech therapy got him on the right track.

So, thank you for whatever you do in that field

[Sparky]

There has been a lot of progress in the SGD field in those years (I've been in it for 3 years, on the IT end of it).

My main focus that I have worked on is SGD with alternative input, eye tracking being one of them. It can be amazing and frustrating technology to say the least.

I dislike Tobii for a few reasons - one being they are a competitor - but also their software sucks IMO compared to some alternatives and they seem to be a bit too heavily money-driven as they have been adding things that you cannot do without a monthly subscription fee, some of which are not insignificant