High performance telephone bandwidth speaker independent continuous digit recognition

2005 ◽  
Author(s):  
P. Cosi ◽  
J.-P. Hosoma ◽  
A. Valente
Keyword(s):  
High Performance ◽  
Digit Recognition ◽  
Speaker Independent

scholarly journals Speaker-Independent Digit Recognition Using a Neural Network with Time-Delayed Connections

1992 ◽  
Vol 4 (1) ◽  
pp. 108-119 ◽  
Author(s):  
K. P. Unnikrishnan ◽  
J. J. Hopfield ◽  
D. W. Tank
Keyword(s):  
Neural Network ◽  
Time Delays ◽  
Network Size ◽  
Data Driven ◽  
Digit Recognition ◽  
Feature Detectors ◽  
Self Recognition ◽  
Speaker Independent ◽  
New Ideas ◽  
Natural Classes

The capability of a small neural network to perform speaker-independent recognition of spoken digits in connected speech has been investigated. The network uses time delays to organize rapidly changing outputs of symbol detectors over the time scale of a word. The network is data driven and unclocked. To achieve useful accuracy in a speaker-independent setting, many new ideas and procedures were developed. These include improving the feature detectors, self-recognition of word ends, reduction in network size, and dividing speakers into natural classes. Quantitative experiments based on Texas Instruments (TI) digit databases are described.

Sign in / Sign up

Export Citation Format

Share Document