4th International Conference on Spoken Language Processing
Philadelphia, PA, USA
Hybrid connectionist-hidden Markov model large vocabulary speech recognition has, in recent years, been shown to be competitive with more traditional HMM systems . Connectionist acoustic models generally use considerably less parameters than HMMís, 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.
Bibliographic reference. Cook, G. D. / Robinson, A. J. (1996): "Boosting the performance of connectionist large vocabulary speech recognition", In ICSLP-1996, 1305-1308.