Phonetic feature discovery in speech using snap-drift learning

Authors:
Sin Wee Lee;Dominic Palmer-Brown
Affiliations:
Innovative Informatics Research Group, University of East London, Essex, UK;Innovative Informatics Research Group, University of East London, Essex, UK
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Year:
2006

Citing 1
Cited 8

A massively parallel architecture for a self-organizing neural pattern recognition machine

Computer Vision, Graphics, and Image Processing

A modal learning adaptive function neural network applied to handwritten digit recognition

Information Sciences: an International Journal
Meta-adaptation: neurons that change their mode

NN'08 Proceedings of the 9th WSEAS International Conference on Neural Networks
Diagnostic feedback by snap-drift question response grouping

NN'08 Proceedings of the 9th WSEAS International Conference on Neural Networks
Modal learning neural networks

WSEAS Transactions on Computers
Extracting road information from recorded GPS data using snap-drift neural network

Neurocomputing
Snap-drift neural network for selecting student feedback

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Snap-drift self organising map

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
2011 Special Issue: Snap-drift neural network for self-organisation and sequence learning

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new application of the snap-drift algorithm [1]: feature discovery and clustering of speech waveforms from non-stammering and stammering speakers. The learning algorithm is an unsupervised version of snap-drift which employs the complementary concepts of fast, minimalist learning (snap) & slow drift (towards the input pattern) learning. The Snap-Drift Neural Network (SDNN) is toggled between snap and drift modes on successive epochs. The speech waveforms are drawn from a phonetically annotated corpus, which facilitates phonetic interpretation of the classes of patterns discovered by the SDNN.