In order to solve these problems, we proposed a single feature vector recognition model based on whole time-frequency information structure of digitspeech.
为了解决这些问题,我们提出了基于数字语音时频信息整体结构的单特征向量识别模型。
2
It describes the implementation of two speech recognisers, for isolated and connected digit recognition.
描述了单呼数字识别和连呼数字识别两种语音识别器的实现。
3
Mandarin digitspeech recognition system has been widely used in different regions in the past decades.