Adaptive Frequency Cepstral Coefficients for Word Mispronunciation Detection

TL;DR

This paper introduces an adaptive frequency warping technique for cepstral coefficients that improves the accuracy of detecting non-native pronunciation errors in speech recognition-based language learning tools.

Contribution

It proposes a novel adaptive frequency warping method that enhances feature representation for better mispronunciation detection in speech recognition systems.

Findings

Adaptive frequency scale improves classification accuracy.

Higher detection rates compared to conventional methods.

Effective in distinguishing native and non-native pronunciations.

Abstract

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.