Fallside, F and Lucke, H and Marsland, TP and O'Shea, PJ and Owen, MSJ and Prager, RW and Robinson, AJ and Russell, NH (1990) Continuous speech recognition for the TIMIT database using neural networks. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 1. pp. 445-448. ISSN 0736-7791Full text not available from this repository.
Four types of neural networks which have previously been established for speech recognition and tested on a small, seven-speaker, 100-sentence database are applied to the TIMIT database. The networks are a recurrent network phoneme recognizer, a modified Kanerva model morph recognizer, a compositional representation phoneme-to-word recognizer, and a modified Kanerva model morph-to-word recognizer. The major result is for the recurrent net, giving a phoneme recognition accuracy of 57% from the si and sx sentences. The Kanerva morph recognizer achieves 66.2% accuracy for a small subset of the sa and sx sentences. The results for the word recognizers are incomplete.
|Divisions:||Div F > Machine Intelligence|
|Depositing User:||Cron Job|
|Date Deposited:||07 Mar 2014 12:01|
|Last Modified:||27 Nov 2014 19:24|