Learn More
Modeling phonological units of speech is a critical issue in speech recognition. In this paper, our recent development of an overlapping-feature-based phonological model that represents long-span contextual dependency in speech acoustics is reported. In this model, high-level linguistic constraints are incorporated in automatic construction of the patterns(More)
Tracking-by-detection methods have been widely studied and some promising results have been obtained. These methods use discriminative appearance models to train and update online classifiers. They also use a sliding window to detect samples which will then be classified. Then, the location of the sample with the maximum classifier response will be selected(More)
A new, data-driven approach to deriving overlapping articulatory-feature based HMMs for speech recognition is presented in this paper. This approach uses speech data from University of Wisconsin's Microbeam X-ray Speech Production Database. Regression tree models were created for constructing HMMs. Use of actual articulatory data improves upon our previous(More)
Spinal cord injury (SCI) is one of the most disabling diseases. Cell-based gene therapy is becoming a major focus for the treatment of SCI. Bone marrow-derived mesenchymal stem cells (BMSCs) are a promising stem cell type useful for repairing SCI. However, the effects of BMSCs transplants are likely limited because of low transplant survival after SCI.(More)
Bone marrow mesenchymal stem cells (BMSCs) have the ability of self-renewal and multi-directional differentiation. Recent reports showed that BMSCs could differentiate into endocrine cells of pancreas. However, the differentiation is not efficient enough to produce insulin-producing cells for the future therapeutic use. Pdx-1 is a crucial regulator for(More)
Language-independent embedded speech recognition is a necessary and important application. Considering personal privacy, collection difficulty of all the reference words, and limited storage space of mobile devices, language-independent (LI) embedded speech recognition should be classified into lightweight speaker-dependent (SD) cases. Dynamic time warping(More)
A corpus linguistic study is reported in this paper, guided by articulatory phonology and by general phonetic principles of speech production. A direct application of this study is the construction of Hidden Markov Model topologies for automatic speech recognition, taking into account integrated multilingualism with the consideration of the common(More)
We describe a robust speech understanding system based on our newly developed approach to spoken language processing. We show that a robust NLU system can be rapidly developed using a relatively simple speech recognizer to provide sufficient information for database retrieval by spoken language. Our experimental system consists of three components: a speech(More)
Grammar-based speech recognition systems exhibit performance degradation as their vocabulary sizes increase. Data clustering is deemed to reduce the proportionality of this problem. We introduce an approach to data clustering for automatic speech recognition systems using kohonen self-organized map. Clustering results are used further to build a language(More)
We present a novel methodology for the representation of sentences by fuzzy semantics, which is applied to the measurement of synonymy. The novelty of this methodology lies in a new way of dealing with the semantics of words and their functions in a sentence. Through the concept of "information mass", a fuzzy semantic construct, a multidimensional(More)