English

Automatic Pronunciation Assessment -- A Review

Computation and Language 2023-10-24 v1 Sound Audio and Speech Processing

Abstract

Pronunciation assessment and its application in computer-aided pronunciation training (CAPT) have seen impressive progress in recent years. With the rapid growth in language processing and deep learning over the past few years, there is a need for an updated review. In this paper, we review methods employed in pronunciation assessment for both phonemic and prosodic. We categorize the main challenges observed in prominent research trends, and highlight existing limitations, and available resources. This is followed by a discussion of the remaining challenges and possible directions for future work.

Keywords

Cite

@article{arxiv.2310.13974,
  title  = {Automatic Pronunciation Assessment -- A Review},
  author = {Yassine El Kheir and Ahmed Ali and Shammur Absar Chowdhury},
  journal= {arXiv preprint arXiv:2310.13974},
  year   = {2023}
}

Comments

9 pages, accepted to EMNLP Findings

R2 v1 2026-06-28T12:57:34.378Z