Domain-aware mispronunciation detection and diagnosis method proposed

Arxiv CS.SD (Sound/Audio ML)

The paper introduces a method for constructing language-specific statistical graphs for mispronunciation detection and diagnosis in computer-assisted language learning. The approach improves model performance on non-native speech.

speech

Arxiv CS.SD (Sound/Audio ML)·Huu Tuong TuHanh NguyenThien Van LuongNguyen Tien CuongVu HuanNguyen Thi Thu Trang

6 days ago