TY - GEN
T1 - Hybrid nn/hmm-based speech recognition with a discriminant neural feature extraction
AU - Willett, Daniel
AU - Rigoll, Gerhard
PY - 1998
Y1 - 1998
N2 - In this paper, we present a novel hybrid architecture for continuous speech recognition systems. It consists of a continuous HMM system extended by an arbitrary neural network that is used as a preprocessor that takes several frames of the feature vector as input to produce more discriminative feature vectors with respect to the underlying HMM system. This hybrid system is an extension of a state-of-the-art continuous HMM system, and in fact, it is the first hybrid system that really is capable of outperforming these standard systems with respect to the recognition accuracy. Experimental results show an relative error reduction of about 10% that we achieved on a remarkably good recognition system based on continuous HMMs for the Resource Management 1000-word continuous speech recognition task.
AB - In this paper, we present a novel hybrid architecture for continuous speech recognition systems. It consists of a continuous HMM system extended by an arbitrary neural network that is used as a preprocessor that takes several frames of the feature vector as input to produce more discriminative feature vectors with respect to the underlying HMM system. This hybrid system is an extension of a state-of-the-art continuous HMM system, and in fact, it is the first hybrid system that really is capable of outperforming these standard systems with respect to the recognition accuracy. Experimental results show an relative error reduction of about 10% that we achieved on a remarkably good recognition system based on continuous HMMs for the Resource Management 1000-word continuous speech recognition task.
UR - http://www.scopus.com/inward/record.url?scp=77951013924&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:77951013924
SN - 0262100762
SN - 9780262100762
T3 - Advances in Neural Information Processing Systems
SP - 763
EP - 769
BT - Advances in Neural Information Processing Systems 10 - Proceedings of the 1997 Conference, NIPS 1997
PB - Neural information processing systems foundation
T2 - 11th Annual Conference on Neural Information Processing Systems, NIPS 1997
Y2 - 1 December 1997 through 6 December 1997
ER -