Source decomposition of acoustic variability in a modular connectionist network
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 129-131 vol.1
- https://doi.org/10.1109/icassp.1991.150295
Abstract
A modular connectionist network model for capturing invariant relationships between the acoustic signal and phonetic categories is developed. The model addresses variations in the acoustic manifestation of phonemes as a function of loudness, speaker identity, speaking rate, and phonetic context. These sources of variation are referred to separate specialized network modules. Each module transforms the representation of its input signal in order to normalize the effect of different source variables. Components of the model have been tested on isolated words for speaker-adaptive vowel recognition (97%) and context-dependent vowel recognition (99.7%). A model integrating amplitude-normalization, speaker-normalization, and context-modulation for continuous speech recognition is under development.Keywords
This publication has 3 references indexed in Scilit:
- Speaker normalization using second-order connectionist networksThe Journal of the Acoustical Society of America, 1990
- Phoneme discrimination using connectionist networksThe Journal of the Acoustical Society of America, 1990
- Context-modulated discrimination of similar vowels using second-order connectionist networksThe Journal of the Acoustical Society of America, 1989