ASR-Free Pronunciation Assessment

Sitong Cheng, Zhixin Liu, Lantian Li, Zhiyuan Tang, Dong Wang, Thomas Fang Zheng

Most of the pronunciation assessment methods are based on local features derived from automatic speech recognition (ASR), e.g., the Goodness of Pronunciation (GOP) score. In this paper, we investigate an ASR-free scoring approach that is derived from the marginal distribution of raw speech signals. The hypothesis is that even if we have no knowledge of the language (so cannot recognize the phones/words), we can still tell how good a pronunciation is, by comparatively listening to some speech data from the target language. Our analysis shows that this new scoring approach provides an interesting correction for the phone-competition problem of GOP. Experimental results on the ERJ dataset demonstrated that combining the ASR-free score and GOP can achieve better performance than the GOP baseline.

 DOI: 10.21437/Interspeech.2020-2623

Cite as: Cheng, S., Liu, Z., Li, L., Tang, Z., Wang, D., Zheng, T.F. (2020) ASR-Free Pronunciation Assessment. Proc. Interspeech 2020, 3047-3051, DOI: 10.21437/Interspeech.2020-2623.

  author={Sitong Cheng and Zhixin Liu and Lantian Li and Zhiyuan Tang and Dong Wang and Thomas Fang Zheng},
  title={{ASR-Free Pronunciation Assessment}},
  booktitle={Proc. Interspeech 2020},