ISCA Archive Interspeech 2005
ISCA Archive Interspeech 2005

Revising Perceptual Linear Prediction (PLP)

Florian Hönig, Georg Stemmer, Christian Hacker, Fabio Brugnara

Mel Frequency Cepstral Coefficients (MFCC) and Perceptual Linear Prediction (PLP) are the most popular acoustic features used in speech recognition. Often it depends on the task, which of the two methods leads to a better performance. In this work we develop acoustic features that combine the advantages of MFCC and PLP. Based on the observation that the techniques have many similarities, we revise the processing steps of PLP. In particular, the filter-bank, the equal-loudness pre-emphasis and the input for the linear prediction are improved. It is shown for a broadcast news transcription task and a corpus of children's speech that the new variant of PLP performs better than both MFCC and conventional PLP for a wide range of clean and noisy acoustic conditions.


doi: 10.21437/Interspeech.2005-138

Cite as: Hönig, F., Stemmer, G., Hacker, C., Brugnara, F. (2005) Revising Perceptual Linear Prediction (PLP). Proc. Interspeech 2005, 2997-3000, doi: 10.21437/Interspeech.2005-138

@inproceedings{honig05_interspeech,
  author={Florian Hönig and Georg Stemmer and Christian Hacker and Fabio Brugnara},
  title={{Revising Perceptual Linear Prediction (PLP)}},
  year=2005,
  booktitle={Proc. Interspeech 2005},
  pages={2997--3000},
  doi={10.21437/Interspeech.2005-138}
}