In this paper, methods of improving the robustness and accuracy of acoustic modeling using decision tree based state tying are described. A new two-level segmental clustering approach is devised which combines the decision tree based state tying with agglomerative clustering of rare acoustic phonetic events. In addition, a unified maximum likelihood framework for incorporating both phonetic and...

Generally, speech recognition systems use context-dependent subword units for recognition. To utilize these units, tree-based state tying is an unavoidable technique. This tying applies linguistic questions to group these units and ties them accordingly. These questions usually require an expensive resource-consumption manual procedure. Even though this problem has been addressed by data-driven...

In this paper, we compare the state-level and model-level tying of continuous density hidden Markov models for the multilingual acoustic modelling. Using the model-level tying technique, the number of the language dependent (LD) phoneme models of five European languages were reduced to the desired number. This tying was based on dissimilarity measure between the LD phoneme models in a bottom-up...

Parameter tying is often used in large vocabulary continuous speech recognition (LVCSR) systems to balance the model resolution and generalizability. However, one consequence of tying is that the differences among tied constructs are ignored. Parameter tying can be alternatively viewed as reciprocal data sharing in that a tied construct uses data associated with all others in its tiedclass. To ...

We propose a new class of hidden Markov model (HMM) called asynchronous-transition HMM (AT-HMM). Opposed to conventional HMMs where hidden state transition occurs simultaneously to all features, the new class of HMM allows state transitions asynchronized between individual features to better model asynchronous timings of acoustic feature changes. In this paper, we focus on a particular class of...

In state-of-art large vocabulary continuous speech recognition (LVCSR) systems, HMM state-tying is often used to achieve good balance between the model resolution and robustness. In this paradigm, tied HMM states share a single set of parameters and are nondistinguishable. To capture the fine differences among tied HMM states, a probabilistic classification of HMM states (PCHMM) is proposed in ...

Design conditions for existence of memory-less feedback control for stabilization of discrete-time systems with equality constraints given on the state variables are presented in the paper. The design problem is addressed for linear discretetime systems with equality constraints tying together some state variables. Using the classical memory-less feedback control principle LMI-based procedures ...

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...

The key problem to be faced when building a HMM-based continuous speech recogniser is maintaining the balance between model complexity and available training data. For large vocabulary systems requiring cross-word context dependent modelling, this is particularly acute since many mmh contexts will never occur in the training data. This paper describes a method of creating a tied-state continuou...