Phone-level pronunciation scoring and assessment for interactive language learning

This paper investigates a method of automatic pronunciation scoring for use in computer-assisted language learning (CALL) systems. The method utilizes a likelihood-based `Goodness of Pronunciation' (GOP) measure which is extended to include individual thresholds for each phone based on both averaged native confidence scores and on rejection statistics provided by human judges. Further improvements are obtained by incorporating models of the subject's native language and by augmenting the recognition networks to include expected pronunciation errors. The various GOP measures are assessed using a specially recorded database of non-native speakers which has been annotated to mark phone-level pronunciation errors. Since pronunciation assessment is highly subjective, a set of four performance measures has been designed, each of them measuring different aspects of how well computer-derived phone-level scores agree with human scores. These performance measures are used to cross-validate the reference annotations and to assess the basic GOP algorithm and its refinements. The experimental results suggest that a likelihood-based pronunciation scoring metric can achieve usable performance, especially after applying the various enhancements.

Durability study of eleven years old cement-bentonite cut-off wall material

Comprehensive understanding of the long-term performance of cement-bentonite slurry trench cut-off walls is essential as these mixes may degrade when exposed to aggressive environments or when subjected to prolonged drying. A series of wetting-drying and immersion experiments was carried out to evaluate the durability characteristics of laboratory mixed samples and block field samples from 40 days to 11 years of age. For the wetting-drying tests, the samples buried in medium graded sand were subjected to periodical flooding and drying cycles. They were then used for permeability testing and unconfined compressive strength (UCS) testing. For the immersion tests, the samples confined in perforated molds were submerged in magnesium sulfate solution for 16 weeks and their microstructures were then analyzed using X-ray diffraction (XRD) technique. This paper identifies the effects of contaminant exposure on durability of cement-bentonite and the effects of aging by comparing 11 years old samples to younger samples. Test results showed that young or previously contaminated cement-bentonite mixes are more susceptible to sulfate attack than old or less contaminated mixes. Copyright ASCE 2008.