Modulation Spectrum Equalization for Improved Robust Speech Recognition
Date Issued
2011
Date
2011
Author(s)
Sun, Liang-Che
Abstract
We propose novel approaches for equalizing the modulation spectrum for robust feature extraction in speech recognition. In these cases the temporal trajectories of the
feature parameters are first transformed into the magnitude modulation spectrum. In spectral histogram equalization (SHE) and two-band spectral histogram equalization
(2B-SHE), we simply equalize the histogram of the modulation spectrum for each utterance to a reference histogram obtained from clean training data, or perform the
this equalization with two sub-bands on the modulation spectrum. In magnitude ratio equalization (MRE), we define the magnitude ratio of lower to higher modulation frequency components for each utterance, and equalize this to a reference value obtained from clean training data. These approaches can be viewed as temporal filters that are adapted to each testing utterance. Experiments performed on the Aurora 2 and 4 corpora for small and large vocabulary tasks indicate that significant performance improvements are achievable for all noise conditions (additive or convolutional, different noise types, and different SNR values). We also show that additional improvements are obtainable when these approaches are integrated with cepstral mean and variance normalization (CMVN), histogram equalization (HEQ), or higher-order cepstral moment normalization (HOCMN). We analyze and discuss
reasons why such improvements are achievable from different viewpoints with different sets of data, including adaptive temporal filtering, noise behavior on the modulation spectrum, phoneme types, and modulation spectrum distance.
Subjects
feature normalization
modulation spectrum
robust feature extraction
temporal filter
histogram equalization
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-100-F90942011-1.pdf
Size
23.32 KB
Format
Adobe PDF
Checksum
(MD5):57c856a5b0737a35db5b5ece62ba7ed7