Microsoft speech recognition

I’ve been experimenting with speech recognition technology that’s built into Microsoft Office. The technology has definitely improved since the last time I tried this, which was about four years ago. Having said that, it will probably be another four years before speech recognition is actually a productivity tool rather than a novelty. Still, all things considered, the technology has made great strides. Not bad for a technology that more than one of my professors declared flat out impossible when I was an undergraduate.

After dictating the two paragraphs above, I had to make a half dozen corrections with the keyboard. Even so, it might have still been faster than typing it in by hand. The software is built into Microsoft Word, so all I needed was a microphone. I bought a refurbished Logitech model that plugs right into one of my keyboard's USB ports. The microphone is great; the software is a work in progress.

This is day two of my experiment, and Microsoft cautions me to expect about 85 percent accuracy at this stage. With practice and some more training, I’m told that accuracy can improve to 95 percent. Microsoft offers you a choice of training materials including excerpts from H. G. Wells’ science fiction classic The War of the Worlds, as well as the forward from the less-than-classic The Road Ahead by Bill Gates. A little case of corporate brown-nosing, I guess.

I’ve only tried to type Chinese want to twice before giving up in frustration. The general process involves typing words been using a phonetic alphabet. Once you have spelled a complete sound, the computer displays a menu with all the characters that sound just like it. This menu usually has five or six or a dozen characters. See you can imagine how tedious typing in Chinese is. Assuming speech recognition continues to improve, I can see as scenario in which it becomes the primary way Chinese speakers interact with computers.

The promise of making computers dramatically easier to use for the world's most populous country is one of the reasons Microsoft has set up shop in Beijing to attack this opportunity.

My parents seemed very excited by the demonstration I showed them this afternoon. though my mom seemed more excited by what she thought was that she could speak in Chinese and the computer would translate into English. I suppose that's in the realm of possibility, but it's probably another five years out after they get the voice recognition part working first.

Bottom line: if you want a cheap way to see how far speech recognition has progressed, get yourself a microphone, fire up Microsoft Word, and click on Speech in the Tools menu. You don't have to be cognitive science groupie like me to appreciate the technology. And the program's attempts to understand what you're saying are worth a few laughs, reminiscent of the Apple Newton and Go PenPoint days.

By the way, Microsoft has added a speech recognition capabilities in awaited other applications can use it. For example, I am currently dictating this text into Firefox so I can publish it here on my blog.

VW Passat

OK, my 1998 VW Passat will be the last non-Japanese car I own. After 3 or 4 recalls and randomnly failing components -- first the anti-lock brakes and most recently the ignition control module -- I'm convinced that only the Japanese cracked the code on how to reliably manufacture automobiles.

Having worked with Japanese companies like NEC in my professional life, I can personally vouch for the typical Japanese attention to detail. So from here on out, it'll be Honda or Toyota or a similar brand. Next up: the Honda Odyssey. Even the Japanese models made in the States (as opposed to Japan) are measurably more reliable than anything coming out of Germany or the US manufacturers. Hats off to them!

Aside from reliability, I've been reasonably happy with the Passat. It drives well, gets great mileage (over a few months when I'm on a typical commute route, I average over 28 mpg), and is very spacious (e.g., we can fit three car seats side-by-side in the back). Alas, if they could only marry the functionality with reliability...

Google Web Accelerator

I just downloaded Google Web Accelerator. It's yet another piece of free-and-useful Google software.

I admit I'm a bit of a Google groupie:

• I use Google search exclusively (who doesn't?).
• I've looked at satellite pics of my house on Google maps.
  
• I use Picasa to organize and fix up my photos.
• Before I buy most things, I find market prices on Froogle.
  
• I blog on Blogger.
• I read the Google blog (via RSS in Thunderbird, naturally)
• I've bookmarked Google Labs and 6 other Google sites.
  

There are only a few things I don't do with Google software.

• I use Yahoo's desktop search at work (outstanding Outlook integration and I swear it doesn't hog as many system resources ag Google's) and Copernic at home (because of Firefox and Thunderbird integration).
• I don't use the toolbar because I don't need the fancy features and Google search is already wired into the Firefox UI.
  

As each new Google product hits the wires, you understand more about why Bill Gates is paranoid about Google taking over the desktop (see the interview in the April 18 Fortune cover story). Compared to Microsoft's products, Google's are more useful, more powerful, easier to use, easier to install -- and free.

I mean, just look at Picasa versus Microsoft's pathetic $50-100 photo-management products. (Perhaps even more impressive or daunting, depending on which side of the fence you're on, compare Google's free Picasa to Adobe's $50 Photoshop Album -- for $50, you won't get many "must have" features compared to Picasa.)

Anyway, the Google Web Accelerator works with Firefox (hurrah!) and IE and uses a variety of techinques to speed up Web access for broadband connections. It installed and started without a hitch in Firefox 1.0.3. I've read reports of lots of people having problems with non-Windows browsers and Firefox extensions -- no problems for me, though.

I've only been running it a day, and I'd have to say the speed up is subtle rather than dramatic. Popular pages (excluding secure sites, thankfully) load marginally faster, as do pages you've visited before (e.g., my blog).

It features a clean UI and does a great job of advertising its chief benefit, which is faster downloads. As with many of Google's new features, there are potential privacy issues. The application gets its own privacy page that is separate from Google's generic Privacy Policy. Also, check out:

• ZDNet UK: Google Web Accelerator sparks privacy fears
  
• BetaNews: Google App Speeds Up Web Surfing
  

I haven't visited any forums yet (where the main privacy issues surface), so I'm not too worried. In the few hours I've been online since installing the accelerator, Google claims that I've saved 1.4 minutes. Nothing earth shattering, but those savings will add up over time. And given that the product is free, the ROI is not too shabby.

Java Home Media Option

I continually marvel at the energy, creativity, and productivity of the open source community.

I use Mozilla.org's Firefox and Thunderbird at home, and not just because I'm a Netscape alumni: they really are superior products. You can join in too. (At work, we recently switched to Outlook/Exchange, and I calculate a daily half hour loss in productivity due to the terrible interface for following threaded conversations and the even worse search tool.)

I stumbled on today's gem, the Java Home Media Option for Tivo while trying to solve a problem playing music on my Tivo. With the old Tivo Desktop (1.x), I had a plugin that would convert Windows Media Audio files to MP3 on the fly, so I could play them via the Tivo's wireless connection. The upgrade to 2.0 (which features the must-have Tivo-To-Go) seems to have broken the plugin -- no more playing Windows Media Audio files on my Tivo (I prefer WMA over MP3 because it yield better audio quality for a given file size).

While Googling around, I stumbled across an open-source implementation of the Tivo Desktop that goes beyond Tivo's own product. While it hasn't solved my WMA problem, it lets me do much more from my Tivo, including:

• Get local weather
• See what's playing my nearby movie theaters
• See what's on my computer desktop
• Browse my MP3s using their ID tags (e.g., genre, artist, album, etc.)
• View RSS feeds -- like this blog
  
• Stream radio stations via Shoutcast

It installed seamlessly, and I was up and running in minutes. Amazing. While not as pretty as Tivo Desktop, it has many more useful features, and really showcases the creativity of the open source community. Since it's written in Java, it should run on a Mac, too. One of my friends has been impatiently waiting for Tivo to release its Desktop 2.0 product on the Mac. I emailed the download link to him, so we'll see if it works. If it does, he won't have to wait until Tivo gets around to porting Tivo Desktop 2.0 to MacOS.

Think about it: here is a group of volunteer programmers who are out-developing the professionals at Tivo! So here's my heartfelt "thanks" and "hats off" to:

• The open source community in general
  
• Mitchell Baker, Brian Behlendorf, Brendan Eich, Chris Blizzard, Mitch Kapor, and the dozens of fantastic developers at the Mozilla Foundation. (Mitchell: it's been a long winding road from the days of trusted root Certificate Authorities!)
  
• Leon Nicholls and the many other hard-working volunteers working on Java HMO in particular.