Decision tree state tying based on penalized Bayesian information criterion
نویسندگان
چکیده
In this paper, an approach of penalized Bayesian information criterion (pBIC) for decision tree state tying is described. The pBIC is applied to two important applications. First, it is used as a decision tree growing criterion in place of the conventional approach of using a heuristic constant threshold. It is found that original BIC penalty is too low and will not lead to compact decision tree state tying model. Based on Wolfe’s modification to the asymptotic null distribution, it is derived that two times BIC penalty should be used for decision tree state tying based on pBIC. Secondly, pBIC is studied as a model compression criterion for decision tree state tying based acoustic modeling. Experimental results on a large vocabulary (Wall Street Journal) speech recognition task indicate that compact decision tree could be achieved with almost no loss of the speech recognition performance.
منابع مشابه
Dynamic threshold setting via Bayesian information criterion (BIC) in HMM training
In this paper, an approach of dynamic threshold setting via Bayesian Information Criterion (BIC) in HMM training is described. The BIC threshold setting is applied to two important applications. Firstly, it is used to set the thresholds for decision tree based state tying, in place of the conventional approach of using a heuristic constant threshold. Secondly, it is applied to choosing the numb...
متن کاملPruning of state-tying tree using bayesian information criterion with multiple mixtures
The use of context-dependent phonetic units together with Gaussian mixture models allows modern-day speech recognizer to build very complex and accurate acoustic models. However, because of data sparseness issue, some sharing of data across di erent triphone states is necessary. The acoustic model design is typically done in two stages, namely, designing the state-tying map and growing the numb...
متن کاملBayesian context clustering using cross valid prior distribution for HMM-based speech recognition
Decision tree based context clustering [Young; '94] ・ Construct a parameter tying structure ・ Can estimate robust parameter ・ Can generate unseen context dependent models ・ Minimum description length (MDL) criterion [Shinoda; '97] Bayesian approach ・ Variational Bayesian (VB) method [Attias; '99] ⇒ Applied to speech recognition [Watanabe; '04] ・ Can use prior information ⇒ Affect context cluste...
متن کاملA Comparative Evaluation of GMM-Free State Tying Methods for ASR
Deep neural network (DNN) based speech recognizers have recently replaced Gaussian mixture (GMM) based systems as the state-of-the-art. While some of the modeling techniques developed for the GMM based framework may directly be applied to HMM/DNN systems, others may be inappropriate. One such example is the creation of context-dependent tied states, for which an efficient decision tree state ty...
متن کاملOptimal tying of HMM mixture densities using decision trees
Decision trees have been used in speech recognition with large numbers of context-dependentHMM models, to provide models for contexts not seen in training. Trees are usually created by successive node splitting decisions, based on how well a single Gaussian or Poisson density fits the data associated with a node. We introduce a new node splitting criterion, derived from the maximum likelihood f...
متن کامل