Hasta La Gadget!

Think of voice recognition, and you probably think of Siri. Now, though, the company behind Apple’s tech, Nuance, is planning a cloud-based, cross-platform system which could make the tech properly useful. More »

While more and more devices are beginning to be able to understand what we’re saying, one problem that we face is that not everything that we communicate is in the form of a verbal cue. With that in mind, the roboticists at the Honda Research Institute have been working on a robot that can not only understand words, but other sounds.

HEARBO (the HEAR-ing roBOt) uses a technology called Computational Auditory Scene Analysis to distinguish various sounds from its environment. This allows it to not just pick out verbal communication, but everything from the beep of an alarm clock to the mailman knocking on your front door. It can then use this information to make decisions about what to do.

The specific version of the technology being used for HEARBO is called HARK, an open source library that breaks down the understanding of sounds into three steps: localization, separation and recognition. This allows it to not only distinguish sounds in a noisy location, but exactly where they are coming from. In fact, the technology can nail down the direction that sound is coming from down to 1 degree of accuracy. Currently, the system can distinguish up to four different sounds going on at once, but in theory more microphones could allow it to handle even more sources.

Here’s a short demonstration video showing how the robot can understand what’s going on despite the world’s most annoying alarm clock going off the whole time:

And here’s an example of HEARBO easily distinguishing music from human commands, identifying song attributes, and even dancing a little bit:

So why develop such a robot? The technology could be used for things like robot butlers that could automatically answer the doorbell, or do things like turn off the TV if the kids have been using it for too long.

[via iEEE Spectrum]

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.

Filed under: Misc, Gaming, Software, Samsung

Samsung patent ties emotional states to virtual faces through voice, shows when we’re cracking up originally appeared on Engadget on Tue, 06 Nov 2012 11:41:00 EDT. Please see our terms for use of feeds.

Permalink   |  USPTO  | Email this | Comments

We’re very familiar with Kopin’s Golden-i, but it was surprising that an early collaboration with Motorola Solutions didn’t immediately lead to Motorola selling the head-mounted computer on its own. That odd discrepancy is being patched up now that Motorola Solutions’ HC1 is here. The design keeps its signature micro-display, head tracking and voice commands, but sees a slight repurposing from Kopin’s focus on security: Motorola Solutions’ attention is on giving construction workers, field technicians and soldiers an always-up computer that keeps their hands free when it would be too dangerous (or just unwieldy) to grab a handheld. We haven’t been told if the HC1 has been upgraded to that promised TI OMAP 4 chip, although we do know that there’s an optional camera to bring on the Aliens-style video feeds as well as pairing support that offers cellular data, GPS and voice calls when linked to the right phone or hotspot. Whether or not the HC1 keeps the Golden-i’s $2,500 price is an unknown as well — that said, the corporate emphasis is more likely to see bulk sales of the wearable PC than any kind of scrimping and saving.

Update: You’ll find an official clip for the HC1 after the break. The clip also confirms that there’s no OMAP 4 in this version.

Continue reading Motorola Solutions outs HC1 head-mounted computer, keeps workers’ hands free in sticky situations (update: video)

Filed under: Wearables

Motorola Solutions outs HC1 head-mounted computer, keeps workers’ hands free in sticky situations (update: video) originally appeared on Engadget on Mon, 22 Oct 2012 08:00:00 EDT. Please see our terms for use of feeds.

Permalink   |  Motorola Solutions  | Email this | Comments

Intel at CES promised a partnership with Nuance to give Ultrabooks a taste of ready-made voice recognition, and we’re finally seeing the results at IDF in San Francisco through the launch of Nuance’s Dragon Assistant Beta. As the name implies, this isn’t just a voice dictation engine like that in Naturally Speaking: chatty users can delegate common tasks like playing music, reading social network updates and searching the web. The beta isn’t immediately available as of this writing, but it should go live soon and will be a core part of of Ultrabook software bundles in the near future, starting with the Dell XPS 13 this fall. We’re wondering why Intel is focusing its Dragon Assistant efforts solely on thin-and-lights — the company still makes money from portlier PCs, after all — but we won’t mind as much given the simultaneous launch of a Perceptual Computing SDK 2013 Beta, which lets developers work Dragon recognition into their own apps. More details await after the break.

Continue reading Nuance and Intel team on Dragon Assistant Beta for Ultrabooks, Dell XPS 13 to lead the charge

Filed under: Laptops, Software

Nuance and Intel team on Dragon Assistant Beta for Ultrabooks, Dell XPS 13 to lead the charge originally appeared on Engadget on Wed, 12 Sep 2012 07:29:00 EDT. Please see our terms for use of feeds.

Permalink   |   | Email this | Comments