next up previous
Next: Connected Speech Recognition Up: Speech Recognition with HMMs Previous: Speech Recognition with HMMs

Isolated Speech Recognition

Let us first consider the case of isolated word recognition, which is simpler than connected speech recognition. For isolated word recognition, a single HMM can be built for each word w within a preset vocabulary. This is illustrated in Figure 5, with one left-to-right model (with skips) for each word. With these models one can compute for each word w within the vocabulary, when an acoustic sequence is given. When an a priori distribution P(w) on the words is also given, the most likely word given the acoustic sequence can be obtained by picking the model which maximizes both the acoustic probability and the prior:

The computational cost for recognition is simply the number of words times the cost of computating the acoustic probability for a word (forward computation, equation 5). The recognition time can however be significantly reduced by using search techniques mentioned in the previous section.

  
Figure 6: Example of hierarchical organization of speech knowledge in the topology of an HMM. Each level can be represented by a different weighted transducer or acceptor. Arcs represent transitions and nodes represent HMM states at a certain level (or groups of states at a lower level). Low-level models (e.g. phoneme models) are shared in many places in the overall HMM.



Yoshua Bengio
Tue Oct 7 08:34:36 EDT 1997