Systems based on automatic speech recognition (ASR) technology can provideimportant functionality in computer assisted language learning applications.This is a young but growing area of research motivated by the large number ofstudents studying foreign languages. Here we propose a Hidden Markov Model(HMM)-based method to detect mispronunciations. Exploiting the specific dialogscripting employed in language learning software, HMMs are trained fordifferent pronunciations. New adaptive features have been developed andobtained through an adaptive warping of the frequency scale prior to computingthe cepstral coefficients. The optimization criterion used for the warpingfunction is to maximize separation of two major groups of pronunciations(native and non-native) in terms of classification rate. Experimental resultsshow that the adaptive frequency scale yields a better coefficientrepresentation leading to higher classification rates in comparison withconventional HMMs using Mel-frequency cepstral coefficients.
展开▼
