Steve Collins, our hardware guru, has been experimenting recently with the new wave of smart watches to see how well they work as speech input devices. He’s put together a neat demo showing voice input from a SmartQ Z1 Android watch being sent over wifi to his XBMC media center, where Amulet’s voice recognition software converts the voice commands to actions.
Check out the video here:
You can read more about the technology involved in this thread on the XBMC forum. Let us know if this is an area that interests you.
James Richards at VoxCommando has released a slick new video showing off some of VoxCommando’s latest features.
You already knew VoxCommando worked well for controlling your music and video experience with XBMC, MediaMonkey, iTunes, and other software. Using its extensibility features, however, James has hooked it up to a bunch of his household appliances, so that he can control the TV settings (brightness, movie mode, on/off, etc), cooling fan, whole-house audio, and more.
The video also does a great job of demonstrating how well voice works as a way to have a two-way conversation with your home automation system, by having it remind you of things verbally, asking it questions (and receiving coherent answers), and a lot more. Read the rest of this entry »
Our friends at Whiteman Technology are launching the Delta DVR at DEMO Spring 2012 in Silicon Valley tomorrow. It’s one of the first commercial DVRs based on Windows 7 Embedded running Media Center, and it includes the Amulet Voice Remote as standard.
It’s a very nicely designed piece of equipment, and has some impressive capabilities: Six HD tuners for recording TV, built-in 802.11N for wireless connectivity to all your other media sources within the house, integrated Blu-ray playback, and even a UI interface for downloading games from the app store. Not to mention, of course, full voice control.
If you’re in Santa Clara tomorrow afternoon, 19th April, why not call in to DEMO 2012 at the Hyatt Regency where Ryan will be demonstrating the Delta DVR on the main Demo stage at 3:45 pm. You can also visit Whiteman Technologies throughout the day at pavillion booth #D15.
Amulet users often ask us for additional voice commands to check the weather, perform unit conversion, read news headlines, and so on.
While we hope to incorporate some of these in a future software release, you can do a surprising amount right now using Amulet’s custom command capability, especially when you combine it with some VBScript.
To demonstrate, I’ve written a simple Visual Basic script to fetch the current weather forecast for your city from Yahoo Weather, decode the XML data returned, and speak the result using Amulet’s voice. Below, I walk you through it.
Note: This discussion is quite technical. If you’re comfortable editing text files with Notepad, you should be able to follow along fine, and adjust the script to suit your own purposes. Read the rest of this entry »
From time to time, we get enquiries asking whether the Amulet Voice Remote will work on an Apple Macintosh.
We designed the Amulet for use with a PC — primarily for Windows Media Center — and nobody in the company uses a Mac, so this wasn’t a use we had forseen. Since the Amulet dongle appears as a standard USB audio input device, however, I thought there was a good chance the Mac might recognize it.
(If you missed Part 1, which introduced Amulet Voice Kinect, read it here.)
So after deciding to see if HaarCascades would work at all with the depth-stream from Kinect, I figured I needed to give the first test the best chance of success. There was no point making a half-hearted effort, have it fail and then having to have another go because I wouldn’t have known if the failure was down to some fundamental problem with using the depth-stream with HaarCascades or just because I had poor HaarClassifiers. To give the test the best chance of success I would need several thousand depth images containing the object that I needed the classifier to recognise and several thousand negative images not containing the object. I settled on 2000 of each.
You may have previously seen in videos, early versions of the Amulet software being used with Kinect. Now the music functionality is finished and we’re ready to give it away. If it proves popular then we’ll release a paid version that will include all the other functionality currently in our Amulet Voice Remote product and more…
This video shows how it works:
I thought I’d make a posting to the Amulet blog to explain a bit of the background behind how and why “Amulet Voice Kinect” works the way it does. Read the rest of this entry »
If you’ve been following the Amulet beta software releases, you probably already know that Amulet V3.0 includes full voice support for the popular My Movies 4 plug-in for Media Center.
For everyone else, here’s a preview video showing how well the voice integration works:
If you’re not familiar with My Movies, it’s one of the nicest, most cleanly integrated Media Center plug-ins out there. It presents a very professional and user-friendly front-end to all your TV & Movie media files, automatically provides movie backdrops, descriptions, actor lists, etc. and even lets you store your own DVD titles directly on your Media Center; highly recommended.
Here’s something the video doesn’t show, which you might find interesting: while the SHOW MOVIE command shows details for any movie in your collection, you can bypass this and start the movie immediately, from anywhere in Media Center, by just saying PLAY MOVIEname. I find this very convenient when calling up Toy Story or Winnie the Pooh for the umpteenth time at the request of my three-year-old!
We’d love to hear feedback from those of you already trying out the beta software with My Movies. If you already have an Amulet Voice Remote and want to give it a try, head over to the beta forums and download the latest version.
As some of you know, we’ve been working on moving Amulet’s voice recognition technology into the cloud.
If you’re an existing Amulet Voice Remote user, you’ll know that Amulet’s voice recognition takes place on your home theatre PC. While this works well for Media Center users, it’s not a good fit for the typical settop box provided by your cable or satellite provider, which usually lacks the CPU performance for good quality speech recognition.
Today, with most households having highspeed Internet, it’s feasible to move the voice recognition engine to a remote Internet server. When you talk into your Amulet Remote, X-Box Kinect, or other voice input device, the audio can be streamed across the Internet in realtime, recognized, and the results sent back to your living room, and it all happens fast enough to keep you from getting impatient.
I’ve made a short video to show how well this works in practise. We have an internal prototype Electronic Program Guide (EPG) application we’ve developed, which works with our next generation low-cost audio remote control hardware.
In the demo, you can see me giving voice commands which are processed in realtime by a remote cloud-based recognition engine. The demo was recorded in Ireland, and the cloud server is in the US, so as you can see, distance is no longer a barrier.
We plan to make further announcements about this technology soon — stay tuned!
Anyone who’s ever used the latest speech recognition technologies with a plain old microphone will tell you that the results can be surprisingly good, as long as you stay close to the mic, have no background noise and turn the mic off when you’re not speaking.
But if you wanted to place a mic under your TV and have it listen to you while the TV is on, then good luck! The mic won’t be able to hear you over the TV audio and worse still, the TV content will trigger the speech recognition causing it to execute all sorts of spurious commands.
Well that’s now changed. There are several audio “smarts” built into Microsoft’s Kinect game controller that allow it to sit next to a TV and make speech recognition possible at a range of several meters! I’ve made a couple of videos that show just such a scenario:
I think the Kinect video capabilities such as skeletal tracking and depth sensing have tended to overshadow the audio capabilities of the unit. From my experience with Kinect so far, I think its audio smarts are seriously impressive. Read the rest of this entry »