All-phoneme ergodic hidden Markov network for unsupervised speaker adaptation

The paper proposes an unsupervised speaker adaptation method using “all-phoneme ergodic hidden Markov network” that combines allophonic (context-dependent phone) acoustic models with stochastic language constraints. Hidden Markov networks (HMnet) for allophone modeling and allophonic bigram probabilities derived from a large text database are combined to yield a single large ergodic HMM which represents arbitrary speech signals in a particular language so that the model parameters can be re-estimated using text-unknown speech samples with the Baum-Welch algorithm. Combined with the vector field smoothing (VFS) technique, unsupervised speaker adaptation can be effectively performed. This method experimentally gave fairly better performances compared with the authors´ previous unsupervised adaptation method using conventional phonetic HMMs and phoneme bigram probabilities