Discriminalve cluster adaptive training

Multiple-cluster schemes, such as cluster adaptive training (CAT) or eigenvoice systems, are a popular approach for rapid speaker, and environment adaptation. Interpolation I weights are used to transform a multiple-cluster, canonical, mode (HMM) set representative to a standard hidden Markov model e, of an individual speaker or acoustic environment. Maximum likelihood training for CAT has previously been investigated. However, in state-of-the-art large vocabulary continuous. speech ' recognition systems, discriminative training is commonly employed. This paper investigates applying discriminative training to multiple-cluster systems. In particular,. minimum phone error (MPE) update formulae for CAT systems are derived. In order to use MPE in this case, modifications to the standard MPE smoothing function and the prior. distribution associated with MPE training are required. A more complex adaptive training near trans scheme combining both interpolation weights and in forms, a structured transform (ST), is also discussed within the MPE training framework. Discriminatively trained CAT and ST systems were evaluated on a state-of-the-art conversational telephone speech task. These Multiple-cluster systems ,were found to outperform both standard and adaptively trained systems.