A severe sparse data problem is faced when building HMMs of syllable units due to the uneven distribution of syllables in natural speech. In this paper we present a novel approach to building syllable HMMs which attempts to overcome this problem. The method involves tying the states in syllable models using a bottom-up clustering algorithm and a state similarity measure employing phonetic infor...

The problem of how to estimate variance parameters in client models from scarce data is addressed in the context of textdependent, HMM-based, automatic speaker verification. Variance flooring and variance scaling are investigated as two alternative estimation techniques and are used with or without variance tying on the state level to reduce the number of parameters to estimate. The best result...

In this paper, an m-level optimal subtree based phonetic decision tree clustering algorithm is described. Unlike prior approaches, the m-level optimal subtree in the proposed approach is to generate log likelihood estimates using multiple mixture Gaussians for phonetic decision tree based state tying. It provides a more accurate model of the log likelihood variations in node splitting and it is...

This paper presents a novel predictive information criterion (PIC) for hidden Markov model (HMM) selection. The PIC criterion is exploited to select the best HMMs, which provide the largest prediction information for generalization of future data. When the randomness of HMM parameters is expressed by a product of conjugate prior densities, the prediction information is derived without integral ...

Decision tree based state tying uses so-called phonetic questions to assign triphone states to reasonable acoustic models. These phonetic questions are in fact phonetic categories such as vowels, plosives or fricatives. The assumption behind this is that context phonemes which belong to the same phonetic class have a similar influence on the pronunciation of a phoneme. For a new phoneme set, wh...

HMM-based large vocabulary speech recognition systems usually have a very large number of statistical parameters. For better estimation, the number of parameters is reduced by sharing them across models. The parameter sharing is decided by regression trees which are built using phonetic classes designed either by a human expert or by data-driven methods. In situations where neither of these are...

In this paper, a simplified 2-D second-order Hidden Markov Model (HMM) with tied state mixtures is applied to the face recognition problem. The mixture of the model states is fully-tied across all models for lower complexity. Tying HMM parameters is a well-known solution for the problem of insufficient training data leading to nonrobust estimation. We show that parameter tying in HMM also enhan...

This paper presents effective triphone mapping for acoustic models training in automatic speech recognition, which allows the synthesis of unseen triphones. The description of this data-driven model clustering, including experiments performed using 350 hours of a Slovak audio database of mixed read and spontaneous speech, are presented. The proposed technique is compared with treebased state ty...

A before-and-after experimental design was conducted to evaluate the potential reduction in the risk of musculoskeletal injuries to concrete reinforcement workers when using an automatic rebar tying machine. Eleven (11) concrete reinforcement workers participated in this experiment. All dependent variables (trunk posture, and rebar tying time) were measured before and after implementing the reb...

Square knots are often used in open surgery to approximate tissue borders or tie off tubular structures like vessels or ducts. Three common methods are used for surgical square-knot tying: one-hand tying, two-hand tying, and the instrument-tying technique. Two types of suture placements are studied in both the open and laparoscopic surgical fields. The first called equal length has suture segme...