Persona and in-car navigation devices

This writer for the Washington Post has a problem with the personae of in-car navigation devices, and with speech recognition systems in general. The article a little over the top in its opinions because the writer is trying to be humorous, but it fairly points out that the speech output of devices can become annoying very quickly if not done properly.

Note that the problem as identified isn't necessarily with the sound of the voice, it's the lack of context machines have when giving directions, and the fact that the problem reveals itself over time, as in a long car trip. These things are often not tested well, or tested at all. The article also identifies lack of "naturalness" as a problem with speech systems, but trying to achieve an undefined kind of "naturalness" causes problems as well.

Speech to text: Jott

A few weeks ago I blogged about the Spinvox demo that transcribes a short message and texts it to your cell phone. Then someone pointed me to Jott, which transcribes your message and sends it in email to someone in your phone book. I'm impressed. Voice transcription has come a long way since I started playing with IBMs Via Voice years ago. The old transcription systems were speaker dependent, and required a high quality microphone and a lot of training for the performance to be very good. Spinvox and Jott are doing speaker independent transcription, and from callers on cell phones as well. There are a lot of potential applications out there, just waiting for someone to develop them.

Why Motorola is selling its mobile division

I really appreciate Bruce Nussbaum's blog on innovation and design. His latest piece is on Motorola's sale of its mobile division. He makes the point that Motorola develops great technology, but can't seem to put that great technology to use in products that consumers want to buy. The take away lesson is that companies need a systematic process for moving their R&D into the marketplace.

Voice control of consumer products: Sync

Speech recognition is showing up in consumer products. The 2008 Ford Focus includes Sync, which was designed by Microsoft. The product was reviewed very favorably by Cnet. Sync gets two things very right. First, the speech recognition of the car's audio works well even in a car interior, which is usually a pretty noisy environment. Second, it's easy for the user to connect the car's speech rec system with the user's own Bluetooth-enabled phone. Drivers then have voice control over their own phones. As often happens, the acceptance and usage of the product depends on the product's usability, and in this case Ford gets it right with Sync. I haven't used the system, but I'm impressed with Cnet's review.

Why worry about voice activating communication media inside a car? Ford, for its part, seems to be rethinking its view of a vehicle as a thing that you drive from point A to point B. If you think about a car as an extension of your office or your home, then you start to put in features that you have come to expect in your office or home. Of course, in a vehicle you're constrained by the fact that drivers need to hold onto the steering wheel when they drive, so they need another way to control their communication devices.

Microsoft, for its part, has a vision of turning every phone and PC into an always-on virtual conferencing device, part of their Unified Communication vision. This product fits nicely into that vision. It allows drivers to conduct business while in their vehicles, which, if you commute, is an enormous time saver. People in the voice business sometimes refer to vehicles as "BAMDs" (big ass mobile devices). Ford's Sync is a big step in the direction of turning a lot of vehicles into BAMDs.

Conversations 2007 conference

Just back from the Nuance Conversations 2007 conference in Boca Raton, Fla. I must say, as my first time at this conference it was quite different from the conferences I've attended in the past. There were several good presentations, some pretty modest presentations, and an overload of social events.

The keynote speech was by futurist James Canton. He gave a polished presentation that I thought was a little light on analysis. I heard a lot of buzzwords and some predictions I've been hearing for years, like the influence of artificial intelligence on our lives.

Many of the sessions were devoted to speech interfaces for mobile devices. The mobile keynote was very good. Scott Kliger, Jingle Networks, talked about free directory assistance, and how 800 FREE 411 has taken off. Most impressive was the amount of advertising money that will move from printed phone books-$14 billion-to somewhere else when the books are no longer printed. The free DA services will take a good portion of that. He noted that the most requested single number in the US is California Dept. of Motor Vehicles.

The big news was Nuance's purchase of Viecore. It was announced at one of the keynote talks. That generated some buzz.

One of the final sessions made reference to the keynote speaker, with a presentation on "Top 10 reasons you know your futurist missed the mark." Of the couple I remember, "Refers to 'accessing the Internets,' 'predicts that the Cleveland Indians will win the ALCS.'" I've never heard a conference speaker crack on the keynote speaker before.