Microsoft Speech Recognition and Unified Messaging

by

 

This is a longer post than usual – it’s about Microsoft’s latest speech recognition demo of Vista, Exchange 2007 Unified Messaging and my experience this week as a surprise guest in Microsoft’s keynote address at SpeechTEK 2006 in New York this week.


I’ve been using Vista, Microsoft’s next operating system to be released in 2007, for about four months.  I immediately tried the built-in dictation software and was blown away by how well it worked.  Out of the box, with NO training, it performed better than anything I’d ever experienced and the editing capabilities for the first time (for me at least) made voice control of the PC intuitive and workable.


So . . . I was surprised and disappointed for my industry when I saw the video that circulated last week of the demo crashing and burning right before the eyes of the financial community.  If you haven’t seen it, I’ll spare you the pain by not linking to it, but it was clear that something was very wrong.  My Vista builds were much older and I had experienced for myself recognition that was very different from what I saw in the video.

 

It turns out there was a bug in the audio subsystem that was introduced at the last minute, and killed just as quickly, but it did its damage by once again making people think that speech recognition is never going to work.

 

Now . . . what a difference a week makes! At SpeechTEK 2006 in New York this week and I witnessed for myself the very same demo, and it worked PERFECTLY!  Microsoft even had the guts to joke about the previous failure, “taunting the demo gods” as one journalist put it, and still I expect they made a bunch of people (albeit industry people) believe that we have entered a new era for a technology that has been a long time coming.

 

I was not an uninterested bystander.   Richard Bray, who gave the keynote address on behalf of Microsoft and who runs their Speech Server group, invited me to demo Exchange 2007 Unified Messaging for Microsoft during his keynote address.  I’m pretty comfortable speaking to groups of people, but this was practically my entire industry and we were going to use live systems to do a live demo in real time.  No recorded demos – no net, just a telephone and a chance to either make a good impression or look like an idiot if I screwed up.  I knew the technology worked, because I’ve personally been live on Microsoft’s Exchange 2007 Unified Messaging product for about four months, but I also knew from experience that it would be easy to misspeak or have an AV problem that could hose up everything.  I had also heard that others had not had the best experience in the same room earlier in the event.

 

The keynote started with Rich talking about Microsoft’s investment and long history in speech recognition.  He then introduced Rob Chambers to do the Vista demo.  I admire Rob – he looked really cool and confident as he walked up to the stage. The dictation recognition was perfect and it understood everything Rob said.  He showed how easy it is to change and edit a document and then moved on to controlling the PC with just his voice.  He received several rounds of applause, especially when he changed his wallpaper from the standard Vista wallpaper to a photo of his young son without ever touching the keyboard.  (I’ll bet you’d have to think about how to do it even with the keyboard, which is what was cool about that part of the demo.  He said something like “How do I change the wallpaper?” and Vista walked him through it, all with only his voice.  You’ve got to see it to believe it.  I hope when THIS video makes the rounds that it is half as popular.) When he finished his demo of Vista speech recognition, my first thought was to high-five him for doing such a great demo.

 

My second thought as Rob walked off the stage and Rich began to introduce me, was “Holly crap, I’m up and if I screw up, I’M going to be the guy in next week’s video making the rounds.”  Rich put me at ease by surprising me by starting this part of the presentation with a photo of my FJ Cruiser project and asking if I really had installed an Xbox 360 in it.  I said something like “I’m not sure which is more embarrassing, that I have installed an Xbox in the FJ or that I’ve had to admit that I’m from Boulder, Colorado and I own an SUV.”

 

I then jumped into the demo and showed how in addition to email; I can now access my voice mail and faxes via Outlook and Exchange Server 2007 with Unified Messaging.  For the demo, I used Outlook Web Access which allows me to access email via a web browser.  We listened to a voice mail from Clint Patterson (another jokester) who suggested that “I needed more cow bell” in the demo.


By the way, this was a demo, but it was my real inbox and our live Exchange Server 2007 back in Boulder.  No one behind a curtain and nothing faked and it will be delivered as part of Exchange 2007.  The idea of Unified Messaging has been around for years but it has typically been an integration of a legacy voicemail system, an email server and an add-on to an email client.  With Microsoft’s approach, Exchange 2007 IS your voice mail and while pricing has not been publicly announced, the phrase “Radical Economics” has been tossed around by the analysts.  It means that I now have only one place to go for my office voice mail, my cell phone voice mail, my email, my faxes (I do still get a few faxes and they are usually something I don’t want sitting out on a public fax machine) AND I have only one login.  My IT people love it because they don’t have to manage separate systems and separate directories.  I know some of our customers are justifying the upgrade to Exchange 12 with the savings in maintenance charges on their legacy voice mail systems.

 

Back to the demo – After listening to the voice mail, I walked across the stage to a plain old telephone and dialed my number at Gold Systems.  I logged into Outlook Voice Access and was given the options of listening to my voicemail, listening to my email (and I can respond by voice to anyone but Brad, who hates voicemail), calling anyone at Gold Systems or (I really like this) anyone in my personal contacts.  Finally, I can do some very interesting things with my calendar which is what I showed next.

 

I said “Calendar” into the receiver and the system replied with something like “You have a meeting in progress entitled SpeechTEK Keynote address with Richard Bray from 8:30 AM to 10:00 AM.”  It offered some options but I interrupted and said “Next.”  It said, “Your next meeting is entitled “Breakfast with Clint Patterson” and again I interrupted and said “Cancel the meeting.”  I was asked to confirm that I really wanted to ditch Clint for breakfast, which I did, but I accepted the offer to send a voice message along with the cancellation notice.”  I responded “Clint, I have no idea what More Cowbell means and I told you they wouldn’t get the joke.  I’m going to have to skip breakfast as I’m still on stage here with Rich.”  I pressed a button on the phone to indicate I was done talking (maybe I could have just stopped talking?  I don’t know, I haven’t tried it) and I said “Send it with Priority”.  The meeting was canceled, Clint was sent an email with my voice note and my calendar in Outlook was updated.

 

For the next meeting on my schedule, I interrupted the system again and said into the phone, “I’ll be 30 minutes late”.  I know a LOT of people who could use this feature!  (I’m fine with you being late occasionally but let me know, OK?  Now you have no excuse if you are on Exchange 12 with UM)  This time the system sent out meeting notifications saying that I was running 30 minutes late.  I hung up the phone, showed everyone how my calendar had updated automatically, made a few last points and I was done.  Whew!  I was the only non-Microsoftee on stage and I was grateful for the chance to be a part of the keynote.  The other demos went perfectly too and for the rest of the show I felt elated to have been a part of it all.

 

The big announcement at the keynote is that Microsoft is merging what has been known as Speech Server 2007 into what was formally known as Live Communications Server to create the Microsoft Office Communications Server 2007.  I’ll write about THAT in another post, but it’s big news and is going to create a lot of opportunity in the industry.

 

I know I sound like I’m drunk on Microsoft Kool-Aid, and I am a little tipsy from it, but this really is big news and I think it will be good for the industry.


To everyone but my competitors, even most of Microsoft’s competitors, this is going to be good for business because it is going to extend speech recognition throughout the enterprise.  The world of communications in general is going to grow and change in fundamental ways, and a lot of people will benefit from Microsoft’s massive investment in this world. 


To Gold Systems competitors specifically:  Pay no attention to this and keep doing what you are doing. No one is ever going to trust their voice mail, phone calls or important business to a PC.  After all, when was the last time you rebooted your mainframe?  Just keep repeating that and maybe this will all go away.  But I doubt it.

 

 

Former Gold Systems building for lease

by

Some of my fondest memories of Gold Systems are from when we were located at 4865 Riverbend Road.  Long before starting the company I used to drive by the office park and think how cool it would be to work in those buildings, and it actually happened.  4865 was the second building we were in, and it was brand new at the time.  Jim and Jeanne Fetterman designed and built two of the buildings in the office park and they did a great job.  Our building had several balconies and it was a lot of fun to have meetings outside.  More than one snowball fight was started from the balcony too.

I don’t care for Class A space, but I want people to feel good about where they work and it helps if it is interesting too.  This building was reasonably priced but very nice.  For a small company the building couldn’t be beat.

Jim just emailed me and said there is space available again in the building, and the one next to it.  If you need about 3,000 square feet or less in Boulder, Colorado, be sure and check it out.  It’s great space and Jim was a wonderful landlord.  He was always quick to do maintenance and when we broke the water line pulling fiber between the buildings and had to backhoe up his brand new parking lot, he was very gracious and understanding – but that’s another story for another day.

Embellishing Resumes

by

One of the headlines at MSN.com today was "Resume Tricks – 6 ways to embellish without lying"

I see a lot of resumes – I don’t read a lot of resumes – but I see a lot of resumes.  The resume has to be special, or from someone that we’re seriously considering hiring before I will take the time to actually read it.  At best, I scan most resumes quickly.  If I have no reason to care about the resume, and that applies to most of the resumes I see, a typo or spelling mistake will generally cause me to hit the delete key.  (The only time I look at paper resumes is if someone at my company or the candidate hands it to me.  Mailing me a resume is a waste of paper I’m afraid.  Also, I’m a terrible speller.  My fourth grade teacher said I’d never be a success if I didn’t learn to spell.  The jury’s still out on that, but I do proofread and I always use spell-check, and I expect people who want to work here to do the same.)

The article referenced above is better than the headline suggests, so I’ll give the author the benefit of the doubt.  A special headline editor probably wrote the headline to grab attention, but for me it was negative attention.  I have two problems with their choice of words.  "Resume Tricks"  I don’t like it already.  According to dictionary.com, a trick is "An act or procedure intended to achieve an end by deceptive or fraudulent means."  Given that definition, if I have the slightest suspicion that a candidate is trying to trick me, I move on to the next person.  The consequences of hiring a dishonest person are too great to even take a chance on someone who might otherwise look good on paper.

"Embellish without lying" is an interesting phrase.  It might be possible.  Again according to dictionary.com, one definition of "Embellish" is "To make beautiful, as by ornamentation; decorate."  People rarely ornament or decorate their resume, so maybe I have the wrong definition.  (Tell you what, I’ll carefully read the next decorated resume that I get – I promise.)  Perhaps the better definition and more common understanding is "To add ornamental or fictitious details to: a fanciful account that embellishes the true story."

Fictitious details could be degrees that weren’t really earned, as the story mentions, or the more common kind of detail such as "saved the company $2.4 million."  How much is a person worth who saved a company $2.4 million – let’s see – $2.4 million, probably more?  So why do I have their resume in my hand, surely they know we don’t pay THAT well and the individual offices at Gold Systems are nice, but that will buy you a great HOUSE, even in Boulder.  My guess is that if they didn’t just make up the number, that they were part of a TEAM who saved the company that kind of money.  When I see a resume that sounds like the person thinks they did it all by themselves, I hit the delete key.  More likely they were standing NEAR the team that did they real work, and they bailed when the project was done.

I LOVE seeing concrete assertions.  Why?  Because then I can check them out.  If you say on a resume that you worked for the fastest growing company in the world, I’m going to do a quick search and see if it’s true.  If I don’t think it is, I’m done, because I figure if you will lie on your resume, you’ll lie on your expense reports and you’ll lie to our customers.

As I said, the article wasn’t that bad, but the headline was terrible.  It isn’t OK to trick or embellish on a resume.

Marketing Blog

by

Sam Decker writes a blog about Marketing and I’m regularly finding interesting posts and links to other good marketing ideas.  I usually read blogs via a NewsGator RSS reader, most recently the beta version of NewsGator Mobile, so I don’t often actually visit the websites of the blogs I read.  I happened to go to Sam’s site tonight and noticed that he and I have similar tastes in books.  I was really surprised to see that he lists my blog as one he reads – thanks Sam!

Website fixed?

by

My web hosting company, PowWeb has up til now done a great job of hosting my website, but last week they migrated me to a new server but didn’t save, or migrate, my CNAME settings.  I think I have it fixed now, but I don’t do this stuff often enough to be sure.  Apparently after messing it up, PowWeb had no way to go back and retrieve the old settings.  Oops.

They did survey me after the fact to see how things went.  We’ll see if they respond.

Minor website problem

by

My web hosting company is moving my site and it looks like I have a bit of a problem.  It’s better now, but there still are some broken image links to fix.  I’m aware of it and I’m working to fix it.

Thanks!  — Terry

Great PocketPC navigation applications

by

I just discovered a great application for my Treo 700w Windows Mobile Device.   Virtual Earth Mobile (VEM) is a tiny mapping application that connects wirelessly to Microsoft’s MSN Virtual Earth.  Moments after downloading the app directly to my phone, I was typing in addresses and getting directions.  I’ve tried other applications that required me to load maps to the phone, and I never had the right map when I needed it. This application gets all of its data from MSN, so there are no maps to load.

It also seems to work world-wide which is a lot of fun.  I typed in "Spain" into the find field, and got a map of Spain.  Besides viewing maps, a click of the stylus will overlay aerial photos.  Give it two addresses and it will give directions formatted for the small screen of a mobile device.  You can even find local points of interest such as "restaurants."

If you happen to be reading this from your Windows Mobile Device, you can get the CAB file direct from http://www.viavirtualearth.com/VVE/Gallery/VEMobile/VirtualEarthMobile.cab

The developer, Jason Fuller, not only has released this as freeware, but he’s made the source code available too!  I think this is going to be one of my favorite applications.  Thanks Jason!

Happy Anniversary Part II

by

June 28th was Gold Systems’ Anniversary, and today is my 15th anniversary at Gold Systems.  My first day as a full-time employee was Independence Day, 1991.  I couldn’t even spell entrepreneur back then!  We made our first sale in the first month, but didn’t recognize revenue or take in cash until the 4th quarter of 1991 if I remember right.  I also don’t remember when I took my first paycheck but it was much later in the year and it was either take a paycheck or go back to work at a real job.

Thanks again to everyone who helped make this all possible!

Toyota FJ Cruiser Car Computer Update

by

I’ve had quite a few people ask for an update on the FJ Car Computer project.  One of my goals with this project is to see where the state of the art is for aftermarket systems, and then push beyond that by installing a real computer with all the bells and whistles I can think of to install.

Phase One of the project was to install a Pioneer AVIC-Z1.  Because I wanted the best speech recognition combined with navigation, audio and other features, this unit seemed like the perfect choice.  After using it for a couple of months, I have mixed feelings about it and I find I can’t really recommend it which is too bad because it is close to being a great system.

The AVIC-Z1 is interesting because it has a 30gb hard drive in it.  You press a button on the face of the unit and the LCD screen folds down automatically uncovering the slot for the CD or DVD. (Yes, it will play movies, but it has interlocks to prevent watching movies from the front seat while the vehicle is moving.)  If you put in a new CD, it automatically rips the CD to the hard drive so you can leave your CD collection at home.  The entire Gracenote database is installed on the hard drive, so for most CDs the system magically plugs in the artist, album name and track data.  I was surprised that it even knew about CDs that were released after I bought the AVIC-Z1.

The hard drive, my iPod and the radio gives me all of the music I would ever want, so I didn’t get the optional XM Radio module.

The display is a touch-screen that is very nice and easy to read and there are a lot of display options.  You can upload photos and associate them with locations in the GPS unit, you can change the wallpaper and do some other neat tricks.

I also went with the iPod interface, the backup camera and a Bluetooth adapter to allow handsfree phone control.  I didn’t originally get the steering wheel remote, but soon realized that it was almost required to use the speech recognition.  It looks a little cheesy I think, but you’ve almost got to have it.

I didn’t install the system myself – Woody at Extreme Autoworks did it for me, and he did a great job.  None of the problems I’m having with the unit should reflect on Woody – I’ll be going back to him for help with phase two of the project.

Even now I’m torn about how to write about the shortcomings of the unit.  It is a shame that Pioneer got so much right, but missed on some really important features.

My first problem was that the Bluetooth connection to my Palm Treo 700w kept dropping after a minute or two.  The advertisements make it sound like the unit will work with any "Bluetooth compatible phones."  I guess they parse that sentence differently than I did.  When I emailed tech support, I received a terse reply of "If the phone is a PDA type it will not work properly."  Wow – that’s a broad statement but when I tried it with an LG "PDA type phone" it would also drop the connection between the unit and the phone.  I found it hard to believe because it seems to me that the sort of person who would rip their radio out of the dash and replace it with this unit, which costs as much as a good laptop, might also likely have a "PDA type phone" in their pocket.

The first email response wasn’t what I’d want my tech support team writing either.  They could have thanked me for my purchase, told me they were sorry that there was an incompatibility problem and suggested some sort of alternative.  I got to trial a Motorola Q phone for a couple of weeks when they came out, and it DID work with the unit.  I sent another email to Pioneer, and copied their PR group to confirm the statement that had been made earlier and I got a much nicer email back, but the result was the same.  The AVIC-Z1 won’t work with the Palm Treo 700w and apparently many other PDA type phones (whatever that means) and it isn’t Pioneer’s problem, according to Pioneer.  When I asked them where I could find their list of compatible phones, I was told that they don’t publish it but that they would be happy to check the list for any phone I might be interested in.  Seems like a silly way to do it to me, and I haven’t had the energy to play 20 questions to find a phone that might work.

Now for the speech recognition.  I have no idea who makes the speech recognition engine.  For some reason the aftermarket automotive companies don’t advertise who makes the speech engine or even the operating system.  The speech engine works amazingly well, except for when it doesn’t, and then it is really, really bad.  I can reel off a 10 digit phone number and it gets it every time.  Other commands always work too, but I still haven’t figured out some of the basics.  The system has a very large vocabulary, but if you don’t say exactly what it is expecting you’re likely to be routed to some far off city.  It’s bad, and much of it is due to poor human factors design, in my opinion.  For instance, it says "Please" before almost every prompt.  After awhile you want to say "Please stop saying Please!"  A simple tone would have been fine I think.  Once again a nice cheat sheet would have been a great help.  If a user can’t figure out the basics pretty quickly, they get frustrated and give up on the more advanced features.  A cheat sheet helps to get them going so that they want to explore and learn more.

Without the steering wheel remote, you have to find the icon on the screen and press it to get prompted for a voice command.  It sort of defeats the purpose to have to look down at the screen while you are driving, and to make it worse, the icon moves around depending on what screen is displayed.  A button on the unit would have been better so at least you’d be able to find it by touch.

Last weekend I used a $400 Garmin GPS that I liked a lot better for navigation.  They know how to design a user interface – I never looked at the manual and was able to use every feature of the unit within a very short time.  It isn’t fair to compare the two units, but if I was just looking for a great GPS, I’d go with the Garmin.

There is a lot to like about the Pioneer AVIC-Z1, but I can’t recommend it.  There is still hope because Pioneer could release a software update and fix most of the problems I’ve experienced, but I wouldn’t buy one until they do.

Phase Two will be to build a computer that will supplement, if not replace the AVIC-Z1.  If you remember the early days of computing where you bought parts and built it yourself, or you wish you hadn’t missed that era, then you might consider building a car computer.  It feels a lot like the early days, except we have the Internet to connect all the nuts in the world who think this sounds like a fun way to spend the weekend.  I’ve been playing with Microsoft Vista for a couple of months, and it is definitely the operating system to use if I can build enough power into the system to run it properly.  The speech recognition in Vista is amazing, but I’ll write more about that another time.

Happy Anniversary Gold Systems!

by

Happy Anniversary Gold Systems!  Last week was Gold Systems’ fifteenth anniversary and I want to thank everyone who helped make it possible.  There are many, many people who contributed to the success of the company.  Past and present employees, partners, customers (lots of customers!), investors, friends and family.

I have to name two people because if not for them I know Gold Systems would not exist today.  My good friend and co-founder Jim Fudge uttered the words "Why don’t we start a company" and then put all is energy and money into making it a reality.  If not for him, we never would have started.  My good friend and spouse, who prefers to remain nameless in my blog, kept me going when I wanted to quit, put more than one $20 bill in my pocket when I was broke and generally has been a good sport about going along for the roller-coaster ride.

There are many other people who deserve thanks and who have been critical to our success.  Thank you!

Terry

Words you want to hear

by

One of my investors just said, just keep doing what you’re doing.  It was so nice to hear that, I started fantasizing about other things I’d like to hear this week.

From a customer:  We need your help figuring out how to spend more of our budget with you.

From a partner:  Both my marketing and product development budgets were unexpectedly increased, and we want to direct it all your way.

From my IT department:  Your new Motorola Q phone arrived today and we already have it syncing with your new Vista laptop, and we didn’t spend any budget because we finally ebayed the old equipment we had in storage.

I’ll stop there and get back to doing what I was doing . . . feel free to add to the list.