Computers have been taught to act and speak, but the problem is how to【C1】______them to listen --to understand spoken words.【C2】______speech recognition systems have been used by workers who need to enter data into a computer while their hands and eyes are otherwise【C3】______ The recognition of a limited vocabulary of single words from a single speaker is【C4】______much a solved problem. Some systems, however, have trouble【C5】______the noise of crumpling(弄皱,变皱)paper from the sound of a human【C6】______ Independent systems【C7】______recognize the same word【C8】______spoken by many different people can be built by sampling how several people say the same words【C9】______storing several patterns for each word. But the chances for error are greater and the vocabulary must usually be【C10】______. Even more difficult is continuous speech. People【C11】______running words together and even changing some sounds when they speak, m the computer【C12】______knows when one word ends and another starts,【C13】______the process much more difficult. It was reported that it【C14】______an hour on the largest computer in【C15】______use to recognize one second of continuous speech. Some【C16】______have been made to improve continuous speech recognition【C17】______giving the. computer some rules of grammar to restrict which words can【C18】______which other words. A device has been developed that has a 5000-word vocabulary but requires the speaker to【C19】______between words. These devices, however crude at the moment, will represent the【C20】______applications of what is considered a promising but extremely difficult technology. 【C1】