Pattern discovery in continuous speech using Block Diagonal Infinite HMM

We propose the application of a recently introduced inference method, the Block Diagonal Infinite Hidden Markov Model (BDiHMM), to the problem of learning the topology of a Hidden Markov Model (HMM) from continuous speech in an unsupervised way. We test the method on the TiDigits continuous digit database and analyse the emerging patterns corresponding to the blocks of states inferred by the model. We show how the complexity of these patterns increases with the amount of observations and number of speakers. We also show that the patterns correspond to sub-word units that constitute stable and discriminative representations of the words contained in the speech material.