Hybrid NN/HMM-Based Speech Recognition with a Discriminant Neural Feature Extraction

In thispaper, we present a novelhybridarchitecture forcontinuousspeech 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 infact, itis the first hybridsystem thatreally 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.

• Type: Conference
• Year: 1997
• Where: NIPS
• Authors: Daniel Willett, Gerhard Rigoll
• Keywords: Continuous Hmm System, Continuous Hmms, HMM System, NIPS 1997, NIPS 2007