Gerhard Rigoll, Daniel Willett. A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction. In Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98, Seattle, Washington, USA, May 12-15, 1998. pages 9-12, IEEE, 1998. [doi]
Abstract is missing.