Modified k-mean clustering method of HMM states for initialization of Baum-Welch training algorithm

Pauline Larue (1) , Pierre Jallon (1) , Bertrand Rivet (2)

1 CEA-LETI - Commissariat à l'énergie atomique et aux énergies alternatives - Laboratoire d'Electronique et de Technologie de l'Information
2 GIPSA-VIBS - GIPSA - Vision and Brain Signal Processing

Hidden Markov models are widely used for recognition algorithms (speech, writing, gesture, ...). In this paper, a classical set of models is considered: state space of hid- den variable is discrete and observation probabilities are modeled as Gaussian distributions. The models parame- ters are generally estimated with training sequences and the Baum-Welch algorithm, i.e. an expectation maxi- mization algorithm. However this kind of algorithm is well known to be sensitive to its initialization point. The problem of this initialization point choice is addressed in this paper: a model with a very large number of states which describe training sequences with accuracy is first constructed. The number of states is then reduced using a k-mean algorithm on the state. This algorithm is com- pared to other methods based on a k-mean algorithm on the data with numerical simulations.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Pauline Larue, Pierre Jallon, Bertrand Rivet. Modified k-mean clustering method of HMM states for initialization of Baum-Welch training algorithm. EUSIPCO 2011 - 19th European Signal Processing Conference, Aug 2011, Barcelone, Spain. pp.951-955. ⟨hal-00620012⟩