Improving mispronunciation detection using adaptive frequency scale

Systems based on automatic speech recognition (ASR) technology can provide important functionality in computer assisted language learning applications. This is a young but growing area of research motivated by the large number of students studying foreign languages. Here we propose a Hidden Markov Model (HMM)-based method to detect mispronunciations. Exploiting the specific dialog scripting employed in language learning software, HMMs are trained for different pronunciations. New adaptive features have been developed and obtained through an adaptive warping of the frequency scale prior to computing the cepstral coefficients. The optimization criterion used for the warping function is to maximize separation of two major groups of pronunciations (native and non-native) in terms of classification rate. Experimental results show that the adaptive frequency scale yields a better coefficient representation leading to higher classification rates in comparison with conventional HMMs using Mel-frequency cepstral coefficients.

Figure optionsDownload as PowerPoint slideHighlights
► A mispronunciation detection system with context adaptive Cepstral features is presented.
► The new features are derived from the Mel-Frequency Cepstral Coefficients by optimizing the frequency warping scales.
► The frequency scales associated with the new features are optimized with respect to pronunciation quality.
► The new features are shown to outperform their counterparts in mispronunciation detection.