I was traveling a lot last week and ended up calling United frequently for flight information. They use a voice recognition system to provide that data. Horrible idea.
In a previous job, I worked on speech recognition systems and know that in general they work OK in quiet environments. But in noisy places, they have a really hard time because they can’t filter out background noise from the person speaking.
With the sound of jet engines, other passengers and frequent announcements, I would often get bad information or be asked to repeat myself. If I did get through a step, it would often ask for confirmation (“I think you said San Francisco, is that correct?”), giving the system another chance to get lost by interpreting background noise as a “no”.
In another exchange, for a flight that made multiple stops, the system prompted me for the city I wanted. Again, it gets lost in background noise. It would have been faster to play the information for both cities.
The designers of speech rec systems, including the United one, try to inject personality into the prompts, making them longer and again increasing the opportunity for misrecognition. They need to keep the prompts as short as possible and provide the information as fast as possible.
Rakesh Agrawal's blog 
5 responses
I rarely get voice recognition to work for me either. Even in a car on the beltway the other traffic is enough to confuse the prompter.
Was there an option to speak to a rep? There should always be the option.
[…] Flight information is a great SMS application – it requires little input and the answer can be delivered in 160 characters or less. It’s faster than trying to use the mobile Web browser to get to the airline’s Web site and navigate through the menus. And it sure beats trying to get the information through the voice-activated phone system. […]
[…] written before about the perils of voice recognition. Many voice recognition systems I deal with just aren’t acceptable. This one actually works. […]
What makes speech-to-text so difficult?…
For command and control (e.g. “play iPod”), speech recognition is actually quite good. The main issues tend to be around endpointing, barge-in detection and background noise. (See https://blog.agrawals.org/2006/08/15/can-you-understand-me-now/ for mor…
What can airlines and airports do today to increase efficiency and reduce annoyance/stress?…
I agree with many of Michael Wolfe’s points. Here’s a few others: * Push back on the insanity and idiocy that is the TSA. These are your customers who are being harassed. Virtually everyone in the industry knows the agency is a joke and doesn’t do a…