Content Copyright © 2006 Bloor. All Rights Reserved.
Question 1: What does a blind man have in common with a car driver? Answer: Neither of them can see the screen of their mobile phone.
Question 2: What does a person suffering from RSI have in common with a car driver? Answer: Neither of them should use their hands to control their mobile phone.
Automatic speech recognition (ASR) and text to speech (TTS) are technologies that have been developed over many years. They run on servers to support telephony and automated call centre applications. Installed on the PC they support dictation as a convenient input method and, importantly, make the PC accessible to people with disabilities.
Over the years the technologies have improved in quality, function and performance. This, along with the greater function and performance of the latest Series 60 mobile phones, means that ASR and TTS can now be implemented on mobile devices.
Nuance Communications Inc. (formerly Scansoft) is most widely known for the dictation software Dragon Naturally Speaking but provides voice input and output across a wide range of technologies.
Voice input and output on a mobile phone opens up a multitude of new opportunities:
- Completely hands free operation for drivers has obvious benefits.
- For blind users voice input is attractive but having SMS read to you means you can join in the biggest use of mobile telephony by young people.
- About one in five of the adults in America is functionally illiterate. The ability to navigate by voice and be able to just say ‘phone my lawyer’ again brings a whole section of the population into the 21st century.
- If you have RSI or any other upper limb problem you will not want to use fiddly buttons or small pointing devices and talking to the phone would be ideal.
- Using your thumbs a lot for texting has been shown to cause RSI so talking to the phone will reduce the cases of a debilitating condition.
- As mobile devices become more multi-functional (phone, camera, diary, address book, MP3 player) the navigation becomes more complex. Talking would be ideal ‘Play me Bob Dylan All along the Watchtower’ or ‘What is my next appointment?’ would be great benefit to any user.
ASR and TTS provides benefits both to able-bodied and disabled users and this is an example of a technology that is essential for the disabled being very useful to the wider population.
Nuance also recognised the problems of people with limited vision. On the PC they commonly use a screen magnifier that will increase the size of one part of the screen. This does not work well on a small form factor as the menus and the buttons are separated and cannot be seen at the same time when the screen is magnified. Nuance have solved this problem by providing a distributed view which keeps the relevant bits of the heading buttons and options on the screen at the same time.
I am sure as these technologies become more powerful and pervasive we will see more innovative solutions that will benefit people with disabilities and the wider population. What about a voice controlled iPod?