LipSync

Latest

  • University of Washington / Ira Kemelmacher-Shlizerman Lab

    Researchers make a surprisingly smooth artificial video of Obama

    by 
    Mallory Locklear
    Mallory Locklear
    07.11.2017

    Translating audio into realistic looking video of a person speaking is quite a challenge. Often, the resulting video just looks off -- a problem called the uncanny valley, which states that human replicas appearing almost but not quite real come off as eerie or creepy. However, researchers at the University of Washington have made some serious headway in overcoming this issue and they did it using audio and video of Barack Obama.

  • HDMI 2.0 officially announced: 18Gbps bandwidth, 60fps 4K, 32 channel audio

    by 
    Richard Lawler
    Richard Lawler
    09.04.2013

    Only just after it leaked out, the folks at HDMI Licensing are announcing HDMI 2.0 officially. Arriving just in time for the wide rollout of a new generation of Ultra HDTVs, it adds a few key capabilities to the connection standard. With a bandwidth capacity of up to 18Gbps, it has enough room to carry 3,840 x 2,160 resolution video at up to 60fps. It also has support for up to 32 audio channels, "dynamic auto lipsync" and additional CEC extensions. The connector itself is unchanged, which is good for backwards compatibility but may disappoint anyone hoping for something sturdier to support all of those suddenly-popular dongles. The cables won't change either, as the group claims current high-speed Category 2 wires can handle the increased bandwidth. Some companies have suggested upgrade paths for their UHDTVs already on the market -- hopefully we'll find out more about those plans this week at IFA 2013. Update: The HDMI Forum has listed a few more specs in its FAQ, including that HDMI 2.0 is spec'd to handle up to 1536kHz audio sample frequency, dual video streams for multiple users on a single screen, multi-stream audio to as many as 4 users at once and support for 21:9 widescreen displays. Follow all of our IFA 2013 coverage by heading to our event hub!

  • Samsung patent ties emotional states to virtual faces through voice, shows when we're cracking up

    by 
    Jon Fingas
    Jon Fingas
    11.06.2012

    Voice recognition usually applies to communication only in the most utilitarian sense, whether it's to translate on the spot or to keep those hands on the wheel while sending a text message. Samsung has just been granted a US patent that would convey how we're truly feeling through visuals instead of leaving it to interpretation of audio or text. An avatar could change its eyes, mouth and other facial traits to reflect the emotional state of a speaker depending on the pronunciation: sound exasperated or brimming with joy and the consonants or vowels could lead to a furrowed brow or a smile. The technique could be weighted against direct lip syncing to keep the facial cues active in mid-speech. While the patent won't be quite as expressive as direct facial mapping if Samsung puts it to use, it could be a boon for more realistic facial behavior in video games and computer-animated movies, as well as signal whether there was any emotional subtext in that speech-to-text conversion -- try not to give away any sarcasm.

  • Ask Engadget HD: How to fix lip sync issues?

    by 
    Ben Drawbaugh
    Ben Drawbaugh
    03.24.2010

    One of the downsides to digital video is the audio has a tendency to get out of sync. We see it on broadcast TV as well as Blu-ray Discs, the issue is literally everywhere. Many AV receivers have a audio delay feature, and even some Blu-ray players, but which is the best and exactly how do you calibrate them? There are plenty of test patterns for tweaking everything from contrast, to overscan, but what about audio sync? And other than good reference material, what other techniques do you use to figure out exactly how much delay is needed? Now we realize that HDMI 1.3 has some built in audio sync magic, but while it works on some titles, it makes others worse. So tell us dear readers, please, how exactly do you fix lip sync issues? Got a burning question that you'd love to toss out for Engadget HD (or its readers) to take a look at? Tired of Google's blank stares when you ask for real-world experiences? Hit us up at ask at engadgethd dawt com and keep an eye on this space -- your inquiry could be next.

  • Tengu Black ready to rock your world

    by 
    Vlad Savov
    Vlad Savov
    01.29.2010

    Did you know that some pseudo-scientists pinpointed January 18 as this year's most depressing day? As we gaze out from the Engadget mansions at the leafless trees and listless mood outside, we can't help but agree that January's a bit of a downer. So to pep yourself up geeky style, why not grab an all-new Tengu Black? It seems a faithful reproduction (i.e. identical but for the color) of the white Tengu, a USB plug-in device that listens to your music and tries to lip sync to it with its LED array contorting into "over 14 different facial expressions." Let's face it, with the Robot Apocalypse all but assured, we should be practicing our love of inanimate objects as much as possible. A video reminder of how the older Tengu does its thing awaits after the break.

  • DIY robot mask uses iPhone display to lip sync your drunken Halloween slurrings

    by 
    Paul Miller
    Paul Miller
    09.08.2009

    You know, after getting beat up last year at the Engadget HQ Halloween party for daring to dress up as an iPod, we're ready to exact a little bit of revenge with this most excellent robot mask idea. The idea is simple enough: it simply pairs the MouthOff app with a cardboard box and tinfoil, but the results speak (and lip sync) for themselves. Check out the video how-to after the break.

  • Cinemassively: Animating avatars with CrazyTalk

    by 
    Moo Money
    Moo Money
    06.20.2008

    Reallusion, the company that creates the animated facial expression software, CrazyTalk, embraced Second Life machinima quite some time ago. First, they appeared at real life festivals, then they developed their own plot of land in the virtual world, and now they've created a page on their website that features the works of SL machinimators, as well as a tutorial. In the instructional video, they explain how to use their software to lipsync pictures of avatars, as well as give some tips and tricks.[Thanks, John!]If you have machinima or movie suggestions from any MMO, please send them to machinima AT massively DOT com, along with any information you might have about them.

  • Cinemassively: Second Life Lip Sync Viewer

    by 
    Moo Money
    Moo Money
    02.24.2008

    Second Life machinimators know how hard it is to make characters look convincing without their lips moving. There are a number of tricky solutions, but some resident inventors are simplifying the process. mm Alder created a special client that you can use to run SL, and it will loop lip movement. To demonstrate, he included a scene from an upcoming machinima by Berardo Carboni. If you are interested in this client, please note that there is a normal viewer, and a Windlight viewer, available for download. You can find documentation on the official SL wiki.[Thanks, Mescaline Tammas!]

  • Reallusion opens CrazyTalk 5 beta to public

    by 
    Moo Money
    Moo Money
    12.16.2007

    One of the top questions I'm asked about creating Machinima is how I get my lips to move. Second Life users know all about the struggle to make convincing lipsync dialogue in their movies. The answer to their problem is CrazyTalk, by Reallusion. It doesn't just apply to SLers, though. Any MMO Machinimator can use it, with the help of chromakeying and bezier masks.CrazyTalk, currently released up to version 4.6, allows you to use a picture or screenshot and map facial regions to animate them when combined with audio. They have been in closed beta testing for a couple of weeks for their newest version, CrazyTalk 5, but they just opened it up to the public! You can download the beta and use it until January 15th, 2008. If you haven't tried CT yet, this is the perfect time.

  • Lip syncing Tengu adds some merriment to your USB port

    by 
    Darren Murph
    Darren Murph
    08.03.2007

    We know, you're probably on your third USB hub by now, but even if this forces you to purchase an entirely new machine in order to cram one more USB-powered whatchamacallit into it, it's simply a must. Meet Tengu, the USB lip syncer that politely sits beside your machine until it gets wind of nearby tunes, after which its face lights up and the digital mouth begins to try its best at matching the words coming from your speakers. Unsurprisingly, the design will reportedly be manufactured by none other than Solid Alliance, and while it's hard to realize how awe-inspiring this thing is in just the picture above, click on through for a video demonstration you won't soon forget.[Via EverythingUSB]