首页>
外国专利>
Using a discretized, higher order representation of hidden dynamic variables for speech recognition
Using a discretized, higher order representation of hidden dynamic variables for speech recognition
展开▼
机译:使用隐藏的动态变量的离散化高阶表示进行语音识别
展开▼
页面导航
摘要
著录项
相似文献
摘要
A hidden dynamics value in speech is represented by a higher order, discretized dynamic model, which predicts the discretized dynamic variable that changes over time. Parameters are trained for the model. A decoder algorithm is developed for estimating the underlying phonological speech units in sequence that correspond to the observed speech signal using the higher order, discretized dynamic model.
展开▼