Tokenizing fundamental frequency variation for Mandarin tone error detection

Rong Tong; Nancy F. Chen; Boon Pang Lim; Bin Ma; Haizhou Li

ICASSP 2015accepted0 citations

Tokenizing fundamental frequency variation for Mandarin tone error detection

Rong Tong, Nancy F. Chen, Boon Pang Lim, Bin Ma, Haizhou Li

Abstract

Tone error is commonly observed in tonal language acquisition. Correct tone production is especially challenging for native speakers of non-tonal languages. In this paper, we exploit the fundamental frequency variation (FFV) feature for Mandarin tone error detection. We propose to use FFV through two approaches: (1) Concatenating FFVs along side with standard speech recognition features; (2) Token FFV: Characterizing pitch variation with longer temporal context through GMM tokenization and n-gram language modeling. Our results show that tone error detection improves by incorporating FFV features and the two approaches are complementary to each other.

BibTeX

@inproceedings{icassp2015_tokenizingfundam,
  title = {Tokenizing fundamental frequency variation for Mandarin tone error detection},
  author = {Rong Tong and Nancy F. Chen and Boon Pang Lim and Bin Ma and Haizhou Li},
  booktitle = {ICASSP 2015},
  year = {2015}
}