Speech Recognition

言语识别

In phonetics and computational linguistics, the recognition of human speech through computer analysis; also called automatic speech recognition. The task involves the matching of an input acoustic signal with a vocabulary (of sounds, syllables, words, etc.) stored in the computer’s memory. The more challenging aim of automatic speech recognition is to handle continuous speech. Here the computer is provided with information about typical patterns of phonetic and phonological segmentation, as well as morphological and syntactic information. More advanced simulation, such as those provided by connectionist models, are also used.

语音学和计算语言学指用计算机分析和识别人类言语；也称作自动言语识别。这项任务涉及将输入声学信号与一存储在计算机记忆内的词表（语音、音节、词等）相匹配。自动言语识别最富挑战性的目标是处理连续言语。这种处理需要向计算机提供语音和音系切分的典型模式的信息，以及形态和句法信息。较高级的模式方式，如各种连接主义模型提供的方式，也已被采用。