Speech Technology Magazine

Speech technology works - literally. Technical advances are making itquicker and easier to implement speech recognition technology in the workplace, fromcustomer service centers to sales organizations, and eventually, throughout the entire<@SM>enterprise.

Hand-held recorders offer increased mobility for speech recognition dictation "on-the-go." Recording into a handheld recorder is quite different than dictating directly to the computer for speech recognition. Following are some guidelines that might be used in buying and using recorders.

Speech-to-Text (STT), the automatic creation of text by voice, has always been the flagship of automatic speech recognition (ASR) applications. Converting any string of spoken words to readable text holds out the promise of eliminating the tedium of typing or the cost and delay of human transcription. In order to fulfill this promise automatic speech recognition for transcription should be as easy and casual as asking your assistant to take some notes. The idea is to just add a microphone to a PC and begin speaking.

This year has been one of dramatic strides for Philips, as they became one of the world’s leading companies in the speech recognition industry, particularly in the telephony market. Obviously, the person in charge of all this is generally busy, but we were able to get Paul Celen to sit long enough to discuss the speech industry with us, and Philips’ role in it both now and in the near future.

Inspired by the books Peter Pan, Bedknobs and Broomsticks, and Where the Wild Things Are, researchers at the MIT Media Laboratories constructed a room that guides children through an interactive, multimedia adventure. The room contains furniture, rear-projected walls, speakers, microphones, lights, and several cameras networked to several computers. As many as four children enter the room and are told to "ask the green cabinet for the magic password."

As computers have become more pervasive, it is becoming clear that many people have difficulty understanding and communicating with them. Users feel they should simply state what they want done and are frustrated at having to learn non-intuitive procedures in order to accomplish anything useful.

Little attention has been given to thereadability of automatic speech-generated text beyond the accuracy of its words. We judgeits quality entirely on the basis of the percentage of spoken words accurately reproduced<@SM>in text.

You say "speech recognition." The computer types "wreck the beach." Mistakes like this are common when dictating to your computer, but they also damage the credibility of speech technology in the users’ eyes (or ears).

Just how interactive are traditional IVRs? Sincethe introduction of Interactive Voice Response technology over 10 years ago, manytelephony-based products have infiltrated the marketplace. Some of the most popular uses<@SM>of IVR systems are with automated attendant applications, call routing and information<@SM>retrieval.

That's what it took for me to become Publisher for this issue of the magazine. So here I am pecking at the keyboard writing these few words in what will surely be my only issue as Publisher. Being on the team that is responsible for the magazine's makeover, I am excited about the evolution of the industry and the magazine as we enter the new millenium.