The scope of this basics section is to provide a short introduction to a few topics and concepts which are essential for speech recognition.
- Gaussian Mixture Models (GMM)
Based on a usual normal distribution, multivariate normal distributions and then GMMs are explained.
- Hidden Markov Models (HMM)
Stochastic processes, Markov models and finally Hidden Markov models are explained.
- Expectation Maximization (EM)
An general approach to inference and learning in latent variable models.
- Artificial Neural Networks (ANN)
The basic concepts of neural networks are introduced.