【正文】 p。 Wayne Ward MIT Laboratory for Computer Science, Cambridge, Massachusetts, USA Oregon Graduate Institute of Science amp。 control, data entry, and document preparation. They can also serve as the input to further linguistic processing in order to achieve speech understanding, a subject covered in section. Speech recognition systems can be characterized by many parameters, some of the more important of which are shown in Figure. An isolatedword speech recognition system requires that the speaker pause briefly between words, whereas a continuous speech recognition system does not. Spontaneous, or extemporaneously generated, speech contains disfluencies, and is much more difficult to recognize than speech read from script. Some systems require speaker enrollmenta user must provide samples of his or her speech before using them, whereas other systems are said to be speakerindependent, in that no enrollment is necessary. Some of the other parameters depend on the specific task. Recognition is generally more difficult when vocabularies are large or have many similarsounding words. When speech is produced in a sequence of words, language models or artificial grammars are used to restrict the bination of words. The simplest language model can be specified as a finitestate work, where the permissible words following each word are given explicitly. More general language models approximating natural language are specified in terms of a contextsensitive grammar. One popular measure of the difficulty of the task, bining the vocabulary size and the 1 language model, is perplexity, loosely defined as the geometric mean of the number of words that can follow a word after the language model has been applied (see section for a discussion of language modeling in general and perplexity in particular). Finally, there are some external parameters that can affect speech recognition system performance, including the characteristics of the environmental noise and the type and the placement of the microphone. Speech recognition is a difficult problem, largely because of the many sources of variability associated with the signal. First, the acoustic realizations of phonemes, the smallest sound units of which words are posed, are highly dependent on the context in which they appear. These phoic variabilities are exemplified by the acoustic differences of the phoneme， At word boundaries, contextual variations can be quite dramaticmaking gas shortage sound like gash shortage in American English, and devo andare sound like devandare in Italian. Second, acoustic variabilities can result from changes in the environment as well as in the position and characteristics of the transducer. Third, withinspeaker variabilities can result from changes in the speaker39。 this is called context dependent acoustic modeling. Word level variability can be handled by allowing alternate pronunciations of words in representations known as pronunciation works. Common alternate pronunciations of words, as well as effects of dialect and accent are handled by allowing search algorithms to find alternate paths of phonemes through these works. Statistical language models, based on estimates of the frequency of occurrence of word sequences, are often used to guide the search through the most probable sequence of words. The dominant recognition paradigm in the past fifteen years is known as hidden Markov models (HMM). An HMM is a doubly stochastic model, in which the generation of the underlying phoneme string and the framebyframe, surface acoustic realizations are both represented probabilistically as Markov processes, as discussed in sections,and . Neural works have also been used to estimate the frame based scores。 see section ) were originally collected under the sponsorship of the . Defense Advanced Research Projects Agency (ARPA) to spur human language technology development among its contractors, they have nevertheless gained worldwide acceptance (., in Canada, France, Germany, Japan, and the .) as standards on which to evaluate speech recognition. Third, progress has been brought about by the establishment of standards for performance evaluation. Only