ISCA Archive Interspeech 2005
ISCA Archive Interspeech 2005

Statistical properties of the warped discrete cosine transform cepstrum compared with MFCC

R. Muralishankar, Abhijeet Sangwan, Douglas O'Shaughnessy

In this paper, we continue our investigation of the warped discrete cosine transform cepstrum (WDCTC), which was earlier introduced as a new speech processing feature [1]. Here, we study the statistical properties of the WDCTC and compare them with the mel-frequency cepstral coefficients (MFCC).We report some interesting properties of the WDCTC when compared to the MFCC: its statistical distribution is more Gaussian-like with lower variance, it obtains better vowel cluster separability, it forms tighter vowel clusters and generates better codebooks. Further, we employ the WDCTC and MFCC features in a 5-vowel recognition task using Vector Quantization (VQ) and 1-Nearest Neighbour (1-NN) as classifiers. In our experiments, the WDCTC consistently outperforms the MFCC.


doi: 10.21437/Interspeech.2005-179

Cite as: Muralishankar, R., Sangwan, A., O'Shaughnessy, D. (2005) Statistical properties of the warped discrete cosine transform cepstrum compared with MFCC. Proc. Interspeech 2005, 341-344, doi: 10.21437/Interspeech.2005-179

@inproceedings{muralishankar05_interspeech,
  author={R. Muralishankar and Abhijeet Sangwan and Douglas O'Shaughnessy},
  title={{Statistical properties of the warped discrete cosine transform cepstrum compared with MFCC}},
  year=2005,
  booktitle={Proc. Interspeech 2005},
  pages={341--344},
  doi={10.21437/Interspeech.2005-179}
}