Speech and Language Technology in Education (SLaTE 2013)
Acquisition of the Japanese vowel length contrast can be problematic for nonnative speakers. For these speakers, a CALL system which can automatically recognize whether a particular vowel is being pronounced as long or short could be of great benefit for pointing out their errors and issuing corrective feedback. However, a method that can adequately do this has not been proposed yet. Vowel length recognition is made difficult because the vowel length distinction is dependent on the surrounding vowel durations. HMMs, the standard way of recognizing this distinction, do not make use of this information. Other methods have been proposed to recognize this, but they do not appear viable unless knowledge about the length of other vowels is present. Thus, to derive a method, we conduct perceptual experiments to analyze the mechanism of vowel length perception. From this analysis, we develop an automatic recognition algorithm for vowel length that uses support vector machines (SVMs). We tested this method on a speaking rate corpus, native speech, and non-native speech. The method produced recognition results that are overall superior to HMMs and also more robust against speaking rate differences with an average of a 0.83 correct recognition rate for 3 datasets. The error and non-error classification rates on nonnative speech for this are 0.86 and 0.84 respectively recognition rate for 3 datasets. The error and non-error classification rates on non-native speech for this are 0.86 and 0.84 respectively.
Index Terms: Japanese, vowel length, recognition, speaking rate, perception, CALL
Bibliographic reference. Short, Greg / Hirose, Keikichi / Minematsu, Nobuaki (2013): "Automatic recognition of vowel length in Japanese for a CALL system motivated by perceptual experiments", In SLaTE-2013, 178-183.