Deep hierarchical bottleneck MRASTA features for LVCSR


Hierarchical Multi Layer Perceptron (MLP) based long-term feature extraction is optimized for TANDEM connectionist large vocabulary continuous speech recognition (LVCSR) system within the QUAERO project. Training the bottleneck MLP on multi-resolutional RASTA filtered critical band energies, more than 20% relative word error rate (WER) reduction over… (More)
DOI: 10.1109/ICASSP.2013.6639013


5 Figures and Tables