Speech Recognition


Architecture of an automatic speech recognition system

Today, state-of-the-art systems for automatic speech recognition are based on the statistical approach of Bayes decision rule. The implementation of Bayes decision rule for automatic speech recognition is based on two kinds of stochastic models: the acoustic model and the language model which together are the basis for the decision process itself, i.e. the search for the most probable sentence. These modules of an automatic speech recognition system are characterized as follows:

  • Signal Analysis
  • Acoustic Modelling
  • Search
  •