Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

Statistical Properties of the Warped Discrete Cosine Transform Cepstrum Compared with MFCC

R. Muralishankar (1), Abhijeet Sangwan (2), Douglas O'Shaughnessy (1)

(1) Université du Québec, Canada; (2) Concordia University, Canada

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.

Full Paper

Bibliographic reference.  Muralishankar, R. / Sangwan, Abhijeet / O'Shaughnessy, Douglas (2005): "Statistical properties of the warped discrete cosine transform cepstrum compared with MFCC", In INTERSPEECH-2005, 341-344.