TY - GEN
T1 - Analog auditory perception model for robust speech recognition
AU - Deng, Yunbin
AU - Chakrabartty, Shantanu
AU - Cauwenberghs, Gert
PY - 2004
Y1 - 2004
N2 - An auditory perception model for noise-robust speech feature extraction is presented. The model assumes continuous-time filtering and rectification, amenable to real-time, low-power analog VLSI implementation. A 3mm × 3mm CMOS chip in 0.5μm CMOS technology implements the general form of the model with digitally programmable filter parameters. Experiments on the TI-DIGIT database demonstrate consistent robustness of the new features to noise of various statistics, yielding significant improvements in digit recognition accuracy over models identically trained using Mel-scale frequency cepstral coefficient (MFCC) features.
AB - An auditory perception model for noise-robust speech feature extraction is presented. The model assumes continuous-time filtering and rectification, amenable to real-time, low-power analog VLSI implementation. A 3mm × 3mm CMOS chip in 0.5μm CMOS technology implements the general form of the model with digitally programmable filter parameters. Experiments on the TI-DIGIT database demonstrate consistent robustness of the new features to noise of various statistics, yielding significant improvements in digit recognition accuracy over models identically trained using Mel-scale frequency cepstral coefficient (MFCC) features.
UR - http://www.scopus.com/inward/record.url?scp=10844254706&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2004.1380859
DO - 10.1109/IJCNN.2004.1380859
M3 - Conference contribution
AN - SCOPUS:10844254706
SN - 0780383591
T3 - IEEE International Conference on Neural Networks - Conference Proceedings
SP - 1705
EP - 1709
BT - 2004 IEEE International Joint Conference on Neural Networks - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2004 IEEE International Joint Conference on Neural Networks - Proceedings
Y2 - 25 July 2004 through 29 July 2004
ER -