Spectral Moment Features for Robust Speech Recognition

Add to your list(s) Download to your calendar using vCal

• Pirros Tsiakoulis (Institute for Language and Speech Processing (ILSP))
• Tuesday 31 May 2011, 13:00-14:00
• Cambridge University Engineering Department, Lecture Room 6.

If you have a question about this talk, please contact Kai Yu.

In this talk I will present the SMAC front-end (Spectral Moment features Augmented by low order Cepstral coefficients). The SMAC feature vector comprises the first central spectral moment and the first two cepstral coefficients – C0, C1. The spectral moment component, which the primary one, is essentially a frequency estimate which is computed using a frequency domain Gabor filterbank (mel spaced). It captures the resonant structure of the speech spectrum, while the overall spectral shape is not adequately modeled. This is why the cepstral coefficients are added, the C0 as an energy estimate and C1 as a spectral tilt estimate. A key advantage of the spectral moment vector is that does not require a decorrelation transformation (e.g. DCT ) and hence the representation remains in the frequency domain. A second inherent property is that it has zero mean value. I will show recognition results on the TIMIT , Aurora 2, and Aurora 3 speech recognition tasks in comparison with MFCC and PLP .

This talk is part of the Machine Intelligence Lab Seminar series.

This talk is included in these lists:

• CUED Speech Group Seminars
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge University Engineering Department, Lecture Room 6
• Chris Davis' list
• Guy Emerson's list
• Information Engineering Division seminar list
• Machine Intelligence Lab Seminar
• Trust & Technology Initiative - interesting events

Note that ex-directory lists are not shown.