A study of LVQ learning schedules for ANN speaker identification
- 17 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 902-906 vol.2
- https://doi.org/10.1109/tencon.1994.369180
Abstract
Over the past few years, artificial neural networks (ANNs) based on learning vector quantisation (LVQ) algorithms have received considerable attention as pattern classifiers. LVQ2 is currently the preferred choice for automatic speaker identification (ASI) applications. The paper investigates 76 ANN ASI learning schedules incorporating the main LVQ variants, for a 21 speaker text independent database. It concludes that a one stage schedule based on LVQ1 with weak or no repulsion is at least as efficient as more complex LVQ2 schedules.Keywords
This publication has 10 references indexed in Scilit:
- The optimization of perceptually-based features for speaker identificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Shift-invariant, multi-category phoneme recognition using Kohonen's LVQ2Published by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A text-independent speaker recognition method robust against utterance variationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Text-independent talker identification with neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Text-Dependent Speaker Identification Using Learning Vector QuantizationPublished by Springer Nature ,1990
- Convergence of the Vectors in Kohonen’s Learning Vector QuantizationPublished by Springer Nature ,1990
- Convergence of a neural network classifierPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Adding a conscience to competitive learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Statistical pattern recognition with neural networks: benchmarking studiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Text-dependent speaker verification using vector quantization source codingIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987