| | |
Summary: 1
Utilizing Compressibility in Reconstructing
Spectrographic Data, with Applications to Noise
Robust ASR
Bengt J. Borgstršom, Student Member, IEEE, and Abeer Alwan, IEEE Fellow
Abstract-- In this letter we propose a novel algorithm for
reconstructing unreliable spectrographic data, a method ap-
plicable to missing feature-based automatic speech recognition
(ASR). We provide quantitative analysis illustrating the high
compressibility of spectrographic speech data. The existence of
sparse representations for spectrographic data motivates the
spectral reconstruction solution to be posed as an optimization
problem minimizing the 1-norm. When applied to the Aurora-
2 database, the proposed missing feature estimation algorithm
is shown to provide significant improvements in recognition
accuracy, relative to the baseline MFCC system. Even without an
oracle mask, performance approaches that of the ETSI advanced
front end (AFE) [1], with less complexity.
Index Terms-- Spectral Reconstruction, Missing Features,
Compressibility, Noise Robust Automatic Speech Recognition.
|
