When we emulate speech in a computer, designers need to worry about more than speech recognition and synthesis.  Researchers have found three important aspects of speech that need to be incorporated.  First, speech is interactive.  Few of us can actually hold our part of the conversation without hearing something in return.   Without some form of feedback, our speech will probably increase in speed and probably even in tone.  Research teams at MIT* found that these changes in speech can actually cause the computer to reject commands it would otherwise adopt.  Hence, they incorporated phrases such as “ah ha” that would be uttered at judicious times, and found that it helped the human keep his or her speech in a normal range.  In other words, some utterances in speech are protocols such as those found in networking handshaking.

A second important part of speech is that meaning can be expressed in shorthand language that probably would be meaningless to others if the participants know each other well.  Over time, shared experiences lead to shared meanings in phrases.  For example, occasionally one of my colleagues will utter “1-4-3-2" in a conversation.  Those of us who know him well know this is short hand for “I told you so” (the numbers reflect the number of letters in each of the words).  To others, it makes no sense.  Another colleague, when discussing the potential problems of a strategy I was about to adopt for a meeting, warned me to remember Pickett’s Charge.  Now, to those who know nothing about the American Civil War, this warning tells us nothing.  To those who know about the war, and the Gettysburg confrontation in particular, know that he was telling me that we all face decisions with incomplete information and that we should not become too confident in our abilities in light of that incomplete information.  In fact, he was warning me to  (a) check my assumptions and (b) look for indications of crucial information that could suggest a need to my strategy.  Many historians believe that had Pickett’s charge been successful, the American Civil War might have had a different outcome. 

A third important part of speech is that it is contextual.  A phrase or sentence in context might be totally understandable, but quite baffling out of context.  For this reason, we generally have redundant signals in human interactions.  Somehow that same redundancy needs to be incorporated into human-computer interactions to ensure understandability.

* Negroponte, N., “Talking with Computers,” Wired, Volume 2.03, March, 1994, p. 144.