Title :
Phoneme recognition based on multi-resolution and non-causal context
Author_Institution :
Dept. of Electr. Eng., Maryland Univ., College Park, MD, USA
Abstract :
An alternative view of neural-network-based phoneme recognition using multiresolution ideas and noncausal context is suggested. Some suggestions are made regarding target and error weight functions to improve performance and simplify training. Based on these observations, a simple network with self recurrent links of different delays is proposed and tested on the task of speaker- independent recognition of unvoiced plosives, (p,t,k), with input feature vectors derived from an auditory model
Keywords :
delays; recurrent neural nets; speech recognition; auditory model; delays; error weight functions; multiresolution ideas; neural-network-based phoneme recognition; noncausal context; self recurrent links; speaker- independent recognition; target functions; unvoiced plosives; Artificial neural networks; Automatic speech recognition; Automatic testing; Educational institutions; Humans; Natural languages; Neural networks; Signal design; Signal processing; Speech recognition;
Conference_Titel :
Neural Networks for Processing [1993] III. Proceedings of the 1993 IEEE-SP Workshop
Conference_Location :
Linthicum Heights, MD
Print_ISBN :
0-7803-0928-6
DOI :
10.1109/NNSP.1993.471854
