Connectionist gender adaptation in a hybrid neural network / hidden Markov model speech recognition system
Victor Abrash, Horacio Franco, Michael M. Cohen, Nelson H. Morgan, Yochai Konig · 1992
a s An approach to modeling long-term consistencies in peech signal within the framework of a hybrid Hidden ) s Markov Model (HMM) / Multilayer Perceptron (MLP peaker-independent continuous-speech recognition system e s is presented. Several ways to model male and femal peech more accurately with separate models are disw cussed, one of which is investigated in depth. A method hich combines gender-independent and-dependent MLP y w training is demonstrated, improving recognition accurac hile retaining robustness. A series of network architect e tures (using our training method) for the connectionis stimation of gender-dependent HMM observation probaa bilities are evaluated in terms of recognition performance nd number of additional parameters needed. Experimenr tal evalutation shows a significant improvement in word ecognition accuracy over the gender-independent system with a moderate increase in the number of parameters. 1. INTRODUCTION - t Bourlard and Morgan [1,8] have demonstr...