Reproduce “Beyond Acoustic Sparsity and Linguistic Bias: A Prompt-Free Paradigm for Mispronunciation Detection and Diagnosis” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Haopeng Geng, Longfei Yang, Xi Chen, Haitong Sun, Daisuke Saito, Nobuaki Minematsu
CROTTC-IF detects learner mispronunciations without requiring a canonical transcript at inference. It combines dense, frame-level acoustic predictions from CROTTC with error information transferred by a training-only teacher to a language model. On L2-ARCTIC, it achieves 71.77% detection F1, compared with 69.60% for PER-MDD; this benchmark result does not establish performance on unrestricted spontaneous speech.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.