Abstract Grapheme-based modeling has an advantage over phone-based modeling in automatic speech recognition for under-resourced languages when a good dictionary is not available. Recently we proposed a new method for parameter estimation of context-dependent hidden Markov model (HMM) called

Abstract-Speech recognition is formulated as a problem of maximum likelihood decoding. This formulation requires statistical models of the speech production process. In this paper, we describe a number of sta-tistical models for use in speech recognition. We give special attention to determining

SRILM is a collection of C++ libraries, executable programs, and helper scripts designed to allow both production of and experimentation with statistical language models for speech recognition and other applications. SRILM is freely available for noncommercial purposes. The toolkit supports

of statistical modeling and show how they have been applied to selected problems in machine recognition of speech.

In the case of a trlgr~m language model, the proba-bility of the next word conditioned on the previous two words is estimated from a large corpus of text. The re-sulting static trigram language model (STLM) has fixed probabilities that are independent of the document being dictated. To improve

-space transforms on a large vocabulary speech recognition task using incremental adaptation is investigated. In addition, initial experiments using the constrained model-space transform for speaker adaptive training are detailed.

and an extremely limited state memory. The single-process model is often inappropriate for vision (and speech) applications, resulting in low ceilings on model performance. Coupled HMMs provide an efficient way to resolve many of these problems, and offer superior training speeds, model likelihoods, and robustness

Abstract-The description of a novel type of rn-gram language model is given. The model offers, via a nonlinear recursive procedure, a com-putation and space efficient solution to the problem of estimating prob-abilities from sparse data. This solution compares favorably to other proposed methods

We present two real-time hidden Markov model-based systems for recognizing sentence-level continuous American Sign Language (ASL) using a single camera to track the user’s unadorned hands. The first system observes the user from a desk mounted camera and achieves 92 percent word accuracy

to deal with the variability of two dimensional (2-D) shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation, recognition, and language modeling. A new learning paradigm, called graph