SLAP: a system for the detection and correction of pronunciation for second language acquisition

We describe a system for the training of Second Language Acquisition Pronunciation (SLAP) for nonnative speakers. This speech recognition-based system is designed to mimic the valuable interactions between second-language students aid a fluent teacher. For our system, when a student speaks a word into SLAP´s microphone, it is analyzed to determine the part of the word (if any) that is incorrectly pronounced. A fluent utterance of the word is then played back to the student with emphasis on the mispronounced part of the word. Just as a live teacher naturally does, the difficult part of the word is played back louder, extended in time and possibly with higher pitch. Current products on the market lack robustness and have no provision for playing back and emphasizing the incorrect portion. We demonstrate SLAP on a multisyllabic word to show typical performance.