Computers That Respond to Verbal Commands Reach the Mass Market
NEW YORK (AP) _ When Capt. Kirk issued verbal commands to the computer aboard the U.S.S. Enterprise in the old ``Star Trek″ TV series, it seemed impossible that anyone could really get a machine to respond to the human voice.
Nearly 30 years later, life has surpassed art. Computer and software makers including IBM and Microsoft Corp. are marketing speech recognition products that allow computers to operate by voice. By simply speaking into a microphone, a user can execute a computer’s functions and enter text without touching a keyboard.
``This `hands free’ idea of speech recognition is starting to grow,″ said Nancy Jamison, a computer industry analyst for Dataquest.
There are two types of speech recognition systems. One is called a voice navigator, an inexpensive software system that puts the user in control of the computer’s commands, such as opening files and moving text.
Dictation systems, which run about $1,000, enter text while a user talks. They also manage the computer’s applications.
Until recently, speech recognition systems were found in expensive specialty computers, such as those for the handicapped. But in the last year, the technology has moved toward more broad-based applications.
Many professionals who depend on dictation, like lawyers, doctors and journalists, have taken to these systems, as have the disabled.
Dr. Stephen Herman, a radiologist at The Toronto Hospital, uses the IBM VoiceType Dictation system for OS-2 to do most of his lab and research reports. What used to take days to put together, he accomplishes in one sitting.
``I can dictate my own report, edit it and send it directly to the doctor who needs it,″ Herman said. ``It saves time and steps.″
IBM launched VoiceType in the fall of 1993. It’s capable of recognizing 32,000 spoken words at approximately 70-100 words a minute, with about 97 percent accuracy. A two-hour enrollment session familiarizes the computer with a user’s voice. Once this session is completed, the system is ready for use.
Like most speech systems, VoiceType, which is also available for Windows, works by identifying the speaker’s sound and language pattern, and then converting those phonemes into text. A statistical model breaks down the speech and creates a probable word sequence.
DragonDictate for Windows and Kurzweil Voice for Windows are other popular dictation systems. Both have vast vocabularies that can be updated and require enrollment sessions, which run under 30 minutes.
These systems allow dictation directly into a word processor, unlike IBM’s version, in which the text must be transferred from the program into a word processor.
Phil Terry, a technical trainer at Moody’s Investors Service who has limited hand use due to repetitive strain injury, uses the Kurzweil system as his primary mode of input.
``It’s not as fast as typing,″ he admits, ``but I can do just about everything by voice.″ He sends mail, explores the Internet and does most of his daily work by voice.
Also gaining popularity are voice navigators, which control and command the computer, replacing basic keyboard and mouse functions. They are easier to use than dictation systems and require less or no enrollment time.
One navigator, Microsoft Windows Sound System, directs the computer’s functions through voice commands. This system costs about $60.
Speech systems were first brought into the market in the mid-1980s. But the technology did not initially attract mass appeal, said Bill Meisel, editor of the Speech Recognition Update, a industry newsletter in Encino, Calif.
``Answering machines got people talking to machines,″ Meisel said. ``Now people are realizing so much can be done by speech.″
Analysts expect the market to grow about 30 percent a year. In 1994, the speech recognition market hit about $350 million, but this is projected to jump to $1 billion by 1998, said Walt Tetschner of Voice Information Associates, a research firm based in Lexington, Mass.
Despite the projected market growth, computer companies are striving to perfect the product, making it more user-friendly.
Companies are developing continuous speech recognition, which would let users speak in a faster, more natural manner. The current systems require ``discrete speech,″ with every word needing clear enunciation.
They are also looking to move away from required enrollment sessions, allowing anyone to use the system without first familiarizing the computer with their speech patterns, said Jane Rauckhorst, an IBM spokeswoman.
But analysts say the biggest goal is to get the general public interested in speech recognition.
``When people are exposed to certain goods, they begin to creep into their lives.″ said computer analyst Jamison. ``Once there’s an awareness and acceptance of it (speech recognition), it will find its niche.″