Automatic pronunciation feedback for phonemic aspiration
Vaishali V. Patil, Preeti Rao · 2013
The computer-assisted learning of spoken language is closely tied to automatic speech recognition (ASR) technology which, as is well known, is challenging with non-native speech.By focusing on specific phonological differences between the target and source languages of non-native speakers, pronunciation assessment can be made more reliable.Aspiration, an important phonemic attribute in plosives of Indo-Aryan languages such as Hindi, Marathi and Gujarati, is rarely found in the world"s languages.The improper production of the aspiration contrast is thus often the most important cue to non-native accents of spoken Hindi.A system for the detection of phonemic aspiration in unvoiced and voiced stops based on discriminative acoustic features is shown to be effective for rating non-native accents and providing reliable phoneme-level feedback.