Adaptively Growing Hierarchical Mixtures of Experts

We propose a novelapproach to automaticallygrowing and pruning Hierarchical Mixtures of Experts. The constructive algorithm proposed here enables large hierarchies consisting of several hundred experts to be trained e ectively. We show that HME's trained by our automatic growing procedure yield better generalization performance than traditional static and balanced hierarchies. Evaluation of the algorithm is performed 1 on vowel classi cation and 2 within a hybrid version of the JANUS 9 speech recognition system using a subset of the Switchboard large-vocabulary speaker-independent continuous speech recognition database.

• Type: Conference
• Year: 1996
• Where: NIPS
• Authors: Jürgen Fritsch, Michael Finke, Alex Waibel
• Keywords: NIPS 1996, NIPS 2007, Speaker-independent Continuous Speech, Speech Recognition, Vowel Classi Cation