Shifted-Delta MLP Features for Spoken Language Recognition

  title={Shifted-Delta MLP Features for Spoken Language Recognition},
  author={Haipeng Wang and Cheung-Chi Leung and Tan Lee and Bin Ma and Haizhou Li},
  journal={IEEE Signal Processing Letters},
This letter presents our study of applying phoneme posterior features for spoken language recognition (SLR). In our work, phoneme posterior features are estimated from a multilayer perceptron (MLP) based phoneme recognizer, and are further processed through transformations including taking logarithm, PCA transformation, and appending shifted delta coefficients. The resulting shifted-delta MLP (SDMLP) features show similar distribution as conventional shifted-delta cepstral (SDC) features, and… CONTINUE READING
Highly Cited
This paper has 34 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 25 extracted citations


Publications referenced by this paper.
Showing 1-10 of 15 references

Acoustic, phonetic, discriminative approaches to automatic language identification

  • E. Singer
  • Proc. EUROSPEECH, 2003, pp. 1345–1348.
  • 2003
3 Excerpts

Similar Papers

Loading similar papers…