Vocal Mimicry Using Lyrebird Technology

Lyrebird has created a voice imitation technology that uses deep learning and artificial neural networks to create fascinating and somewhat scary results. It relies on deep learning models developed at the MILA lab of the University of Montréal.

Lyrebird will offer an API to copy the voice of anyone. It will need as little as one minute of audio recording of a speaker to compute a unique key defining her/his voice. This key will then allow to generate anything from its corresponding voice. The API will be robust enough to learn from noisy recordings. Lyrebird will offer a large catalog of different voices and let the user design their own unique voices tailored for their needs.

Users will be able to create entire dialogs with the new or mimicked voice. Inflection, emotion, and content can all be tailored as necessary through a developer API. The demos are fairly impressive but still distinctly robotic. Check out some Trump/Obama examples below.

[soundcloud url=”https://api.soundcloud.com/playlists/318022504″ params=”auto_play=false&hide_related=false&show_comments=true&show_user=true&show_reposts=true&visual=true” width=”100%” height=”300″ iframe=”true” /]

I’m interested to find out how accurate this will be for non-english and non-human verbal communication.

The Murmuration Is The Flock Itself, The Susurrus Is The Sound It Produces


Videos of starling murmurations are numerous yet always enchanting. However, but this clip from Jan van IJken’s documentary short film The Art of Flying is exceptional because of the sound. From the video’s youtube page:

We know a lot of factual information about the starling—its size and voice, where it lives, how it breeds and migrates—but what remains a mystery is how it flies in murmurations, or flocks, without colliding. This short film by Jan van IJken was shot in the Netherlands, and it captures the birds gathering at dusk, just about to start their “performance.” Listen well and you’ll be able to hear how this beautiful phenomenon got its name.

Bruce Springsteen <–> Dolly Parton

If you take Dolly Parton’s song about temptation and slow it down to 33.3 RPM it sounds a lot like Bruce Springsteen. Dolly Parton – Jolene Slowed 33 RPM

If you take Bruce Springsteen’s song about temptation and speed it up to 45 RPM it sounds a whole lot like Dolly Parton. Bruce Springsteen – I’m on Fire 45 RPM

There has to be some sort of secret meaning here but I haven’t been able to figure out yet.

Amazing Grace On The Matryomin Sounds Strangely Wonderful

A matryomin is an unusual instrument. It’s a cross between a miniature, pitch-only, theremin and a matryoshka doll (a Russian nesting doll). The instrument has a cult following in Japan.

This video shows a matryomin ensemble called “Da” at the auditorium of Jiyugakuen Myonichikan in Tokyo on 22 Jan. 2011. The ensemble consisted of 167 musicians playing Amazing Grace. It sounds wonderful – in a strangely creepy sort of way.

Recently the ensemble group Da broke a world record for the “Largest Matryomin Ensemble” by gathering over 277 musicians in concert.

via youtube

Here is a link to the mp3 if you want it: Amazing Grace by Da

Museum Of Endangered Sounds

I love the idea of saving sounds from extinction. Marybeth Ledesma, Phil Hadad and Greg Elwood (under the guise of Brendan Chilcutt) have created and curated the online Museum Of Endangered Sounds. It’s an audio archive of yesteryear’s gadgets and electronics. Without the museum the sounds of analog cameras, dot matrix printers, dial-up modems, Speak & Spells, and floppy disks would have died a silent death. But now I have them archived for my own nostalgic musing. We would have failed as a generation if we didn’t try to preserve and then force our past on the youth of today. Long live Museum Of Endangered Sounds.

(via Alan Cooper)