Hybrid connectionist-hidden Markov model large vocabulary speech recognition has, in recent years, been shown to be competitive with more traditional HMM systems [4]. Connectionist acoustic models generally use considerably less parameters than HMM’s, allowing real-time operation without significant degradation of performance. However, the small number of parameters in connectionist acoustic models also poses a problem - how do we make the best use of large amounts of training data? This paper proposes a solution to this problem in which a "smart" procedure makes selective use of training data to increase performance.