Chapter 11 of the HTK Book describes discrete HMMs, in particular with application to speech recognition. However, as far as I know, the existing continuous HMMs cannot be converted to the discrete ones. You should train them by yourself. The training data (feature vectors) can be converted though (see Section 5.14).
Chapter 11 of the HTK Book describes discrete HMMs, in particular with application to speech recognition. However, as far as I know, the existing continuous HMMs cannot be converted to the discrete ones. You should train them by yourself. The training data (feature vectors) can be converted though (see Section 5.14).