Josh would spend a few hours a day on it if we let him. The first thing he said after he turned it on was ‘Daddy, I need to move my sites over to my new laptop because my old machine is dying.’ That is a direct quote (Kim immediately wrote it down.) Josh uses the kitchen computer which is an old gateway all-in-one imac-ish 266Mhz PIII. It’s not dying so much as it just can’t run the new flash games he likes in realtime. Sadly I can not get the plucky little laptop to run the full www.noggin.com site due to it’s exclusive use of flash 8. There are rumors of a way to get it to work (with both software and hardware hacks as the real problem is the memory required to run such huge flash games.) The same reason why the 266Mhz machine can’t hack it, the XO can’t. I suspected this all along, but so far he has not missed the 1/2 functional flash games.One of his favorite activities on the XO is memorize. It is also the one he is most frustrated with. This is basically just the old memory card game, only it could be letters, simple math, or other matchings. You can create your own match boards, but for some odd reason, the game does not randomize the card placement (and hence his frustration). I noticed this and mentioned it to my wife, and then the next day Josh came to me and said ‘Dad, you need to help me program this. It’s always the same.’ I peeked at the source code and my eyes crossed. I can’t imagine the creators not using a randomization, so it might just be pseudo random and the lacking of a proper seed. I should mention that Josh is 4 (‘4 and a half in two days dad!’) and has been using computers sence he was one and a half. He has an impressive vocabulary, and ran read many words as well. Granted they are all words which show up in flash games; things like ‘Start’, ‘Play’, ‘Pause’, ‘Done’, ‘Next’, ‘Back’, ‘Print’, and ‘Quit’. It is fun to watch him show me how things work. The only activity which has him confused is ‘pipi’. When I told him it was how you program the computer he lit up, but as he can’t write yet, it is more a source of frustration than anything else. The track pad is a little frustrating as there is no tactile difference between the conductive and resistive portions. Right clicking is also an oddity for him. Early on I got a small kids mouse for the kitchen computer and mapped both buttons to a left click. I did this after the fifth time he brought up the flash ‘properties’ and got all confused. All in all, very minor issues.

Now to the Mac. This has been a long time in coming. I grew up on Mac machines. It was not until college that I switched to PC and linux (at the same time no less). This was because of a virus actually. I was fascinated by the Michelangelo virus. this virus actually affected both Mac and PC computers. However I could hack on it on the linux boxen (running the new, easy to install, slackware distribution, installed from 104 floppy diskettes!) The computer lab I was working at ran the new Windows 3.11 environment (not yet an OS) and Wolfenstein 3D was the game of choice (and Civ, Doom, and Scorched Earth… good times, good times…) Well I am back to the Mac, and just in time. Less than 12 hours after getting the machine my old laptop stopped having those pesky hardware faults intermittently; preferring to have them quite consistently during the boot process.So I have been using a Mac for almost 2 weeks. Win2K and XP are now painful for me to use; and I had always thought of Win2K as the best C++ development environment; sorry Unbuntu. I tried using a different laptop the other day and the lack of two finger scrolling and other quick options drove me to distraction. The ‘Command’ button still annoys me a little. Mainly because the control key has been moved over and not every thing has been remapped to command, so hitting control is a pain, which makes emacs less than pleasant. The other issue is the screen resolution. I am used to 1600×1200, and this max out at 1200×900 1440×900. The loss of 30% of my screen height is a real bummer for both browsing and coding. I limit my coding to 80 characters, so the extra wide screen does not gain me much, and the loss of 30% hurts a lot in viewable context. I am sure I will get used to it. To date the only software that I am missing are some obscure codecs for old fansub anime, the ability to write to NTFS volumes and dev studio; sorry there is no better C++ debugger, hate the IDE beyond that. I can live with that. I am trying out vmware to get those 3 things I am missing. The rest is currently native Mac. I can’t believe how easy it was to switch.

My god, I wish I had something good to say about this piece of advertisement. Lets decompose.

1. The product

They somehow took a product that is fun to watch people use, and has a very cool, minimal, embedded interface, and made it a chore to watch. Worse yet, they misrepresented it’s capabilities. It works better, faster, and easier than is portrayed. It is a continuous speech recognizer, why is that kid talking discreetly (one word at a time, and slowly?). It looked like he was using Kurzweil Voice or Dragon Dictate from 1995! Even the executive is talking as if he is reading a cue card (which is most likely the truth of it). This software is used by stenographers in court rooms. The fastest speaker can be recognized. I thought the most precious thing in a commercial was time? Why is there so much filler?

They never actually show the software clearly. The dragon bar is just a yellow blurry blob on the screen. Granted you can hide the bar, but the end result is, the system appears to be very slow and unresponsive. Even the cute typing text in the add is a misrepresentation. We do not send one letter at a time to the screen; that would be annoying after 2 seconds, not to mention slow. At least the womans use of the product is a little closer to reality. Oh and yes, you have full command and control over your PC ala Star Trek, but by saying ‘listen to me’ and ’stop listening’ instead of ‘computer’; though you would never get that impression.

2. The script

Wow. I mean wow. When it comes to emerging trends, technology, and what the ‘hip’ kids are doing, our upper management is fairly on top of things. They also understand the products they sell at a level I have not seen at any other company. I guess the same can not be said of our hired marketing firm (or whoever produced this thing)! The things wrong with the script (from both a technical and substantive perspective):

• The woman writing an e-mail: Even my Mom knows what a signature is and how to set her mail program to include it automatically. Who in their right mind would use a voice macro to do that? There are much better ways to show off macro’s. And form filling would be better for multiple signatures. That is a killer feature!
• The history report. I know adults think teenage boys are stupid and cannot write a decent report, but this poor actor must have been choking back bile when he saw this script.
• The IM interaction. This is just abysmal: ‘Are you in’? Every IM client from hour 0 has had the ‘away’ feature, so yes, he is ‘in’, you know that already. I guess ‘in’ is the hip new lingo all the kids are using these days.
• The executive. This is how a teenage boy pretending to be an executive talks.

3. The acting

All I can say is I really hope we got a good deal here. In some cases I think it is the material. There is not much you can do to make it palatable, so why waste the effort. It is a cut rate commercial for a few basic cable channels after all. What is interesting is we have many commercials for our vendors and resellers, and the acting there is top notch. You can find most of those on youtube, or on our website (though this is a demo, not a commercial).

4. The Direction and Cinematography

Ok, its a commercial. The sets were believable. the lighting spot on, the sound perfect, and the basic camera work was good. But please show the product. You never got a good look at what was going on, on the machine. The product is supposed to be the star of the commercial. Here it appears to be a character off screen being talked about.

What would I have done?

Well I would do a rip off of the HP ‘talking hands’ commercials. This was actually my idea back in 1997 when I first started working with speech. Show the apps swapping around like you do in real life, only by voice. Show the real speed of the product. show the people, but not their heads. Show their feet propped up on the desk in front of them. Put the product first, and make it interesting. Have them standing there, and the transparent screen in front doing all the cool things they do in the HP commercials, only they have their hands behind their back. Show people really using the product, not selling it. I guess that is why I am an engineer and not in marketing.

Additional Notes:

No you do not need to speak punctuation. There is auto-punctuation, but before it is accurate the system needs to have been used for a number of hours to collect enough statistics on how you use punctuation and inflection. Having DNS inspect past e-mails and documents can help, but gathering the inflection data is the key part. For that reason it is turned off be default. More research and data will fix that.

No you do not need to spend hours or even minutes training the system. You can use it right out of the box, and it will get better with time. To be honest the learning curve is more on the user end, than on the software end. Talking to a computer is just like any new means of input, like cell phone SMS tapping, or pen tablet. It takes time to become comfortable with it, but not as much time as other input devices.

This blog post dictated with Dragon Naturally Speaking 9.5 Professional.

This is nothing new really, the jobs listing is 5 pages long for our Burlington Ma. office alone. What is different, is that the group I work in is hiring. That would be the MREC (Modular Recognizer) Group, which does the development on the core speech recognition engine for a multitude of product lines, including Dragon Naturally Speaking, Mobile Solutions, and Medical Transcription Services to name just three. Yes I know the ‘demos’ suck, you can search youtube and find better examples of the products.

The Core MREC team is has always been a small core group of less than 10 engineers working with research and the product groups. Speech experience is not a requirement (and is actually the exception) for our group. We work with research to develop new features and productize new algorithms. The work is primarily C++ on windows and linux. The code base is the cleanest one I have ever worked on (and I have worked on over three dozen in a number of fields). The code is not old either, as we are continually rewriting parts of the engine, removing obsolete features, and adding in new ones; that is where the ‘M’ in MREC comes into play. Python experience is a big plus. The primary research framework is all python and the core engine is instrumented in python.

If this sounds interesting to you, send in your resume, either via the official nuance form, or by e-mailing me (doug at this site). You can also ask questions in comments to this post.

This post was dictated directly into wordpress using Dragon Naturally Speaking 9.