Sparse Auditory Reproducing Kernel (SPARK) Features for Noise-Robust Speech Recognition

作者：Fazel Amin^*; Chakrabartty Shantanu

来源：IEEE Transactions on Audio Speech and Language Processing, 2012, 20(4): 1362-1371.

DOI：10.1109/TASL.2011.2179294

• Auditory HMAX
• gammatone functions
• reproducing kernel Hilbert space (RKHS)
• robust speech recognition
• sparse features

In this paper, we present a novel speech feature extraction algorithm based on a hierarchical combination of auditory similarity and pooling functions. The computationally efficient features known as %26quot;Sparse Auditory Reproducing Kernel%26quot; (SPARK) coefficients are extracted under the hypothesis that the noise-robust information in speech signal is embedded in a reproducing kernel Hilbert space (RKHS) spanned by overcomplete, nonlinear, and time-shifted gammatone basis functions. The feature extraction algorithm first involves computing kernel based similarity between the speech signal and the time-shifted gammatone functions, followed by feature pruning using a simple pooling technique (%26quot;MAX%26quot; operation). In this paper, we describe the effect of different hyper-parameters and kernel functions on the performance of a SPARK based speech recognizer. Experimental results based on the standard AURORA2 dataset demonstrate that the SPARK based speech recognizer delivers consistent improvements in word-accuracy when compared with a baseline speech recognizer trained using the standard ETSI STQ WI008 DSR features.

• 出版日期2012-5