Neural trees-using neural nets in a tree classifier structure
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Hi-index | 0.00 |
This paper presents a Self-Learning Neural Tree Network (SL-NTN) for classification of speech features into phones. The SL-NTN employs a farthest-neighbor fuzzy-clustering algorithm to establish the intra-class correlation among speech phones, thus, splitting the phones in such a way to maximize the recognition performance while reducing the computational complexity. When evaluated on the 61 phones of the TIMIT database, the SL-NTN has shown to provide an 'optimal' trade-off between computational complexity and recognition performance. It also provides insight towards the interrelationship among the applied speech patterns.