Shoebox Is Listening

For all of their increasing versatility, machines lack a vital quality that even the lowliest mutt possesses: they cannot understand their master's voice. This situation may soon change. Last week International Business Machines Corp. demonstrated a small, innocent-looking gadget that may some day permit machines to follow spoken orders, and even eavesdrop on human conversations.

IBM's speech recognizer, called "Shoebox" because it is smaller than a shoe box, so far recognizes only 16 spoken words, including the ten digits and six arithmetical command words such as plus and minus. But this is no mean feat. Earlier attempts to make machines recognize spoken words have run into trouble because they tried to copy the human ear, which analyzes the complicated mixture of sound frequencies in human speech. IBM Engineer William C. Dersch, inventor of Shoebox, thinks that this is like designing an airplane by copying a bird's feathers. His machine does not depend on sound frequencies; it recognizes words by listening for their "asymmetry," an esoteric quality of speech that human ears cannot distinguish but that Shoebox finds as clear as the beat of a bass drum.

Shoebox is not distracted by ordinary room noises--even loud ones--but Dersch talks into its microphone gently and takes pains to pronounce his words completely. Shoebox listens and dutifully prints numbers and symbols on a roll of paper. When it hears "false," it washes out everything it holds in its small memory. It recognizes words spoken fast or slow, or in high or low pitch. It is not disturbed if 'six is pronounced "seex," but it insists on being obtuse if "five" is pronounced "fi'," as is common in rapid speech.

IBM has no immediate plans to graft Shoebox on any of its information-handling machines, but a bright gleam glows in the eyes of its engineers. They will first increase Shoebox's vocabulary to 1,000 words, then to 10,000. This can be done without much difficulty, they think, since multisyllabic words are comparatively easy to recognize. They will also try to make Shoebox recognize mumbled, slurred, and female voices; at present it can handle only the words of clear-spoken males. Most foreign languages are no problem for Shoebox, but it is baffled by Chinese, Bantu and other tongues that depend on tone for their meaning.

When Shoebox grows up, IBM may set it to work taking down spoken words and numbers for such harried people as airplane pilots or supermarket checkers. Later, it may graduate to recording customers' orders, controlling machine tools, or solving mathematical problems. Eventually, the day may come when a troubled scientist or businessman can tell his problem by voice to the listening ear of an electronic computer--and get a spoken oracle answer soon after he stops talking.

This file is automatically generated by a robot program, so reader's discretion is required.