Deep Cnns Along The Time Axis With Intermap Pooling For Robustness To Spectral Variations

Abstract

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.

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keylee2016deep

Related papers

• Advances In Very Deep Convolutional Neural Networks For LVCSR (2016)0.00
• An Improved Deep Neural Network For Modeling Speaker Characteristics At Different Temporal Scales (2020)6.34
• Multistream CNN For Robust Acoustic Modeling (2020)10.21
• Acoustic Scene Classification Using Bilinear Pooling On Time-liked And Frequency-liked Convolution Neural Network (2020)5.84
• Analyzing Deep Cnn-based Utterance Embeddings For Acoustic Model Adaptation (2018)6.77
• Deep Speaker Embedding Learning With Multi-level Pooling For Text-independent Speaker Verification (2019)0.00
• Using Multi-resolution Feature Maps With Convolutional Neural Networks For Anti-spoofing In ASV (2020)3.58
• Deep Convolutional Neural Network-based Inverse Filtering Approach For Speech De-reverberation (2020)7.16