Back to Search
Start Over
A cascaded neuro-computational model for spoken word recognition.
- Source :
-
Connection Science . Mar2010, Vol. 22 Issue 1, p87-101. 15p. 4 Diagrams, 3 Charts, 1 Graph. - Publication Year :
- 2010
-
Abstract
- In human speech recognition, words are analysed at both pre-lexical (i.e., sub-word) and lexical (word) levels. The aim of this paper is to propose a constructive neuro-computational model that incorporates both these levels as cascaded layers of pre-lexical and lexical units. The layered structure enables the system to handle the variability of real speech input. Within the model, receptive fields of the pre-lexical layer consist of radial basis functions; the lexical layer is composed of units that perform pattern matching between their internal template and a series of labels, corresponding to the winning receptive fields in the pre-lexical layer. The model adapts through self-tuning of all units, in combination with the formation of a connectivity structure through unsupervised (first layer) and supervised (higher layers) network growth. Simulation studies show that the model can achieve a level of performance in spoken word recognition similar to that of a benchmark approach using hidden Markov models, while enabling parallel access to word candidates in lexical decision making. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09540091
- Volume :
- 22
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- Connection Science
- Publication Type :
- Academic Journal
- Accession number :
- 49144254
- Full Text :
- https://doi.org/10.1080/09540090903383171