Speech Recognition: The Right to Conversational Free Speech
Remember what it was like before the telephone answering machine? What about the cell phone or the notebook computer? We seemed to get along just fine without these devices, but now that they are so prevalent, life without them seems incomprehensible.
These products are indispensable because they give us freedom, or as defined by the American Heritage Dictionary, they allow us the condition of being free from restraints. No longer do we have to sit by the phone for fear of missing that all-important call. We don't have to worry about being unable to summon help if our car breaks down and we can carry our office wherever we go.
This year the Consumer Electronics Show, the largest annual tradeshow for consumer technology, provided insight into how much freer we can become. CES has consistently been the venue many manufacturers use to introduce their newest products, products including the video cassette recorder (VCR), the camcorder and the DVD, and this year was no exception. Gazillion-inch plasma TVs aside, the show included exhibits of prototype and currently available products that integrate speech recognition or make using speech easier and more effective.
There were microphones, lots of microphones. Analog. Wireless. Bluetooth. From Shure to Plantronics to GN Netcom/Jabra, the new products incorporate enhanced noise-canceling capability. Many of the models offer streamlined designs to make wearing a microphone more comfortable and less conspicuous. While it used to be difficult to find wireless solutions for voice input into the computer, wireless is becoming the norm, allowing desktop dictation users to dictate without being tethered to the computer.
These trends will make desktop dictation a more attractive solution to individuals who may consider using speech for productivity, but who do not need to rely on it because of a physical disability. For individuals who use speech recognition because of physical disabilities, they can now decide when and for how long they want to sit in front of the computer without relying on others to put their headset on or take it off; and they won't get tangled up in the microphone wires.
Hewlett Packard is introducing a line of computers featuring Intel's dual core processor technology. The systems have two processors so there should be less interference if you are running two applications, the result being a noticeable improvement in overall performance. Kevin Wentzel, technical marketing manager for HP, explains the general benefits of a dual-core system, "It [dual core] will help with any application that has multiple processes or multiple threads running at the same time."
This could be a blessing for desktop dictation users. Because desktop dictation is so resource-intensive and is used in conjunction with at least one other program (word processor, Internet browser, etc.), there should be noticeable improvements in the speed and accuracy of dictation. It will be interesting to see if the theory holds true.
XM Radio and Johnson Controls showed voice-enabled in-car solutions. The products, not yet commercially available, offer voice search and retrieval for controlling applications including music selection and operation of navigation systems. Information that is available via satellite will also be accessible by voice.
Magellan, the consumer brand of Thales Navigation, incorporates SayWhere Technology into its Global Positioning System, providing the user with dynamic turn-by-turn guidance. Company representatives say customer response has been positive. The product does not currently accept voice input, but adding this functionality is a logical upgrade path.
SpeechGear, Inc. offers a suite of products that provide instant translation of anything you say, hear, see, write or type. A version for PCs allows conversational free speech and a PDA version uses phrase-building technology. The translation is generated as an audio output and a visual transcript of the conversation. The product is said to accurately maintain the meaning of the sentences. While SpeechGear's products are primarily being used by the military, expect to see travelers making use of the software to communicate while visiting other countries.
We can obtain all the information we could ever want wherever we are and, in many instances, we can use voice as the interface. While this type of access may seem superfluous, can you remember what it was like before you were able to record your favorite TV show?
Robin Springer is the president of Computer Talk ( www.comptalk.com ), a consulting firm specializing in the design and implementation of speech recognition and other hands-free technology services. She can be reached at (888) 999-9161 or firstname.lastname@example.org.