Deep CNNs along the Time Axis with Intermap Pooling for Robustness to Spectral Variations
This work addresses robustness to spectral variations in large vocabulary continuous speech recognition, offering a domain-specific improvement for speech processing tasks.
The paper tackled the problem of acoustic feature variability in speech recognition by proposing a deep CNN with convolution along the time axis and an intermap pooling layer to achieve insensitivity to spectral variations, resulting in a competitive word error rate of 12.7% on the SWB part of the Hub5'2000 test set without speaker adaptation.
Convolutional neural networks (CNNs) with convolutional and pooling operations along the frequency axis have been proposed to attain invariance to frequency shifts of features. However, this is inappropriate with regard to the fact that acoustic features vary in frequency. In this paper, we contend that convolution along the time axis is more effective. We also propose the addition of an intermap pooling (IMP) layer to deep CNNs. In this layer, filters in each group extract common but spectrally variant features, then the layer pools the feature maps of each group. As a result, the proposed IMP CNN can achieve insensitivity to spectral variations characteristic of different speakers and utterances. The effectiveness of the IMP CNN architecture is demonstrated on several LVCSR tasks. Even without speaker adaptation techniques, the architecture achieved a WER of 12.7% on the SWB part of the Hub5'2000 evaluation test set, which is competitive with other state-of-the-art methods.