Speech Technology Magazine

 

Improve the User Experience

Graphical user interfaces have been the standard user interface for computer users for over 20 years. It's time to up-level the user's computing experience by voice-enabling applications.
By James A. Larson - Posted Mar 1, 2006
Page1 of 1
Bookmark and Share

Graphical user interfaces have been the standard user interface for computer users for over 20 years. It's time to up-level the user's computing experience by voice-enabling applications. Voice adds a new dimension to user interfaces by making it easier for users to express their requests.

Here are some new ways users can interact with computers by using their voices and ears:

Browse and talk. Rather than struggling to find the answer to a specific question by chasing links across a Web site, you can simply click a button on the GUI screen and be connected to a human or artificial agent. The agent may provide the information by simply speaking the answer to your question, or guide you through the Web site to the page containing the answer to the user's question. Customers receiving personalized service are more likely to purchase goods and services.

VoIP

VoIP phone calls (even international) are widely regarded as free. However, there is a cost for their Internet service. There are a number of services providing "free" VoIP calls, including Skype,  TheGlobe,  and FWD.  Most standards-based VoIP requires a protocol for transmitting signals between connected parties. Popular signaling protocols include H.323,  Session Initiation Protocol (SIP),  or one of several proprietary protocols (for example, the Skype protocol for Skype applications). To minimize bandwidth requirements without sacrificing quality, speech codecs compress at the source of the audio and decompress at the audio sink. Popular codecs include the ITU-T standards G.711 and G.729. The Aurora distributed speech recognition protocol can also be used as a compression algorithm, delivering its payload directly to a speech recognition engine. VoIP calls can potentially benefit speech recognition by retaining some of the voice frequencies dropped by traditional telephone networks, although VoIP may suffer from packet loss and latency problems.

Shop with a friend. Currently browsing the Web is a solo experience. But with a voice connection, two or more customers talk with each other as they jointly browse the Web and review items for purchase. It will be like going shopping with a friend without leaving your respective homes.

Telephone a computer. Use your telephone or cell phone to talk with Google—search the Web for answers to your questions, extract the information chunks you need, and listen to the results. Talk to your calendar to set up appointments. Speak items into your personal "to-do" list—such as "pick up toothpaste on the way home" or "renew your driver's license before your birthday."

Computer telephones you. A computer calls you with alerts such as "Intel stock has jumped three points," "schools will be closed tomorrow morning due to a projected snowstorm tonight," or "your home team just won their championship game." And it will remind you to perform those little chores that you added to your personal "to do" list. You may want to set some rules as to when you will accept computer telephone calls so the computer doesn't become a nag.

Call home. Ever left on a family vacation only to have your spouse tell you that the oven was left on? Don't turn around and drive home, instead use your telephone or cell phone to call your home area network and verbally instruct the oven to turn itself off.

Until recently, voice transmission has been expensive. Long distance charges over land lines prohibited many people from using voice to interact with the computer or interact with other people while using the computer. This is changing with the rapid introduction of "Voice over Internet Protocol" (VoIP), which enables voice connections for free or minimal cost.

The Internet has made the world a smaller place, enabling users to access information from computers anywhere in the world. Speaking and listening will make computers available to everyone—from a cell phone, telephone, or speech-enabled PDA at work, at home, or on the road. Now is the time to invest in speech-enabled applications that will take advantage of inexpensive voice transmission costs and improve the user's computing experience.


Dr. James A. Larson is manager, advanced human input/output, Intel, and author of the home study course VoiceXMLGuide, http://www.vxmlguide.com.  He can be reached at jim@larson-tech.com.


Page1 of 1