John Lawrence (MSFT) : General Speech Stuff

Web sites are failing visually impaired users - can the Speech Application SDK help?

johnlawr — Wed, 14 Apr 2004 16:10:00 GMT

The BBC has news of an interesting report: Websites 'failing' disabled users

The key finding was that the group worst affected are those with visual impairments, and the article refers to the recent announcement that the British magazine New Statesman is going to be making its web pages available as speech using new software by Texthelp Systems.

The Microsoft Speech Application SDK ought to make it much easier for web developers to create web pages that support visually impaired users through the use of speech. I would like to think that at some point in the future all ASP.NET web developers considered adding speech controls to their pages to support accessibility.

One of our roadblocks right now, however, is that we don't (yet) have an easy web download of our Speech Add-In for Internet Explorer available from the Microsoft web site, and the redistributable that comes with the SDK is rather large (it includes the speech recognition engine, even through it could use the built in engine in Windows XP ).

If you'd be interested in this as a more widely available installer for the Microsoft Speech Add-In, please leave me a comment and I'll make sure it gets passed on to the appropriate people - we're always looking for input to help us evaluate the importance of features like this.

Lots of news coverage on the Microsoft Speech Server 2004 launch

johnlawr — Wed, 25 Feb 2004 00:42:00 GMT

Sadly I don't have much time right now to comment on these, but hopefully they'll make interesting reading.

TechWeb, 2.20.04

"Microsoft Sets Launch Date for Speech Server"

http://www.techweb.com/wire/story/TWB20040220S0004

eWEEK, 02.19.04

"Microsoft Sets March Launch for Speech Server" - Matt Hicks

http://www.eweek.com/article2/0,4149,1530828,00.asp

ENT News, 02.19.04

"Microsoft Speech Server to Launch in March"

Scott Bekker

http://www.entmag.com/news/article.asp?EditorialsID=6131

TMCNet, 2.19.04

"Adtech Solutions Now Provides Computer Telephony Integration for Solutions Employing the Microsoft Speech Server"

http://www.tmcnet.com/usubmit/2004/Feb/1024145.htm

TMCNet, 2.19.04

"Edify and Microsoft to Deliver Integrated Speech Solutions"

http://www.tmcnet.com/usubmit/2004/Feb/1024140.htm

Jason Nadal is working on a Speech2Blog application

johnlawr — Fri, 21 Nov 2003 21:22:00 GMT

Jason Nadal is working on a Speech2Blog application using the Longhorn speech API to take dictation and post it to a blog. Now if the blog page was navigable with the Speech Application SDK speech controls, that would be really cool.

Microsoft PocketPC Voice Command

johnlawr — Tue, 04 Nov 2003 01:54:00 GMT

Microsoft Voice Command for Pocket PC is now available for download at Handango. It supports speech control of your Windows Mobile 2003 device to look up contacts, get calendar information and even control Windows Media Player.

Note that this isn't part of the Speech Application SDK, or the Microsoft Speech Server offerings - it's a completely self contained product running on the mobile device. Congrats to the teams who worked really hard to put this together - getting a recognizer running on such a small device is a great achievement!

I just wish I could run it on my own personal Toshiba e740 Pocket PC - sadly Toshiba decided not to allow the e740 to be upgraded to Windows Mobile 2003, but that's another story....

Help or hindrance?

johnlawr — Fri, 26 Sep 2003 19:22:00 GMT

I read an interesting article on the front page of USA today this morning discussing the pain that people have to go through to get their problems solved when phoning up automated answering systems.

Systems like the Microsoft Speech Server have the potential to make the systems significantly better for end users, but good voice user interface (VUI) design is going to be essential - otherwise things won't be any better than they are right now with touch tone systems.

A good speech based customer support line could do far more than route callers to the right extension number, because speech is a much more powerful input modality than DTMF touch tones. However, if voice based applications simply replace DTMF input with a simple list of spoken options we may not see any improvements - but I'm hoping that our SDK encourages a much more creative approach to speech application development going forward.

Going to SpeechTek

johnlawr — Tue, 23 Sep 2003 21:45:00 GMT

I just found out this morning that I've been lined up to speak at a session at SpeechTek in New York next week.

I'd already been planning to attend, but I'm now going to have a slot to talk about our SDK in the "Application Development Tools and Environments" session, although unfortunately it will only be for about 10 or 15 minutes so probably not enough time for a demo.

Our Speech Application SDK is a fairly new arrival to the broad speech application development community so it's an exciting opportunity to present our approach to application development to potential early adopters of our platform. It will be interesting to see what sort of reaction we get.

I'll definitely be writing up more about SpeechTek over the next week or so - feel free to leave me a comment if you're going to be there.

Crazy Joe

johnlawr — Sat, 23 Aug 2003 06:36:00 GMT

Somebody just sent me a link to this "commercial" for Crazy Joe's Speech Engine - a ISIP public domain speech recognizer. It's pretty amusing - although apparently it features an "award winning team of actors". I'm not quite sure what awards they've won though...