In this article we take a step forward towards the application of Support Vector Machines (SVMs) to continuous speech recognition. As in previous work, we use SVMs to estimate emission probabilities in the context of an SVM/HMM system. However, training pairwise classifiers to discriminate between some of the HMM-states of very close phonetic classes produce unsatisfactory results. We propose a...

In situations when automatic speech recognition (ASR) systems are rapidly deployed for a new task, the availability of within-domain training data may be limited. In such cases one needs to build the ASR system from other, possibly out-of-domain databases. We refer to the process of building ASR systems for one task domain using data from other domains as cross-domain modelling or CDM. Conventi...

This paper introduces a method for regularization of HMM systems that avoids parameteroverfitting causedby insufficient training data. Regularization is done by augmenting the EM training method by a penalty term that favors simple and smooth HMM systems. The penalty term is constructed as a mixture model of negative exponential distributions that is assumed to generate the state dependent emis...

Context-dependent phone models are used in modern speech recognition systems to account for co-articulation effects. Due to the vast number of possible context-dependent phones, statetying is typically used to reduce the number of target classes for acoustic modeling. We propose a novel approach for state-tying which is completely data dependent and requires no domain knowledge. Our method firs...

This paper presents a new method of constructing phonetic decision trees (PDTs) for acoustic model state tying based on implicitly induced prior knowledge. Our hypothesis is that knowledge on pronunciation variation in spontaneous, conversational speech contained in a relatively large corpus can be used for building domain-specific or speaker-dependent PDTs. In the view of tree structure adapta...

In this paper, we propose phoneme duration modeling methods with tree-based state tying. Two kinds of phone duration modeling methods are suggested. The first is context independent phoneme duration model in which duration parameters are stored in each phone. The second is context dependent duration model in which duration parameters are stored in each state being shared by context dependent ph...

We study labor-tying in a competitive agricultural economy. The co-existence of seasonal fluctuations in income and imperfect credit markets suggests that tied contracts should dominate casual labor markets. However, empirical observation from India suggests that this is far from being the case, and indeed, that there is a declining trend in labor tying. We consider a model that permits deviati...