Title :
Neural speech enhancement in the time-frequency domain
Author_Institution :
Dept. of Comput. Eng. VI, Technische Univ. Hamburg-Harburg, Hamburg, Germany
Abstract :
A pulsed neural network approach for the enhancement of speech is presented. It employs a recently introduced pulse-induced masking principle on a joint time-frequency representation of signals. Based on the notion of a spectro-temporal receptive field, the principle provides signal-dependent dictionary elements, which are integrated into an enhancement process in the time-frequency domain. Experiments on signals with different types of noise are conducted with the resulting neural time-frequency domain method.
Keywords :
neural nets; speech enhancement; time-frequency analysis; neural speech enhancement; neural time-frequency domain method; pulse-induced masking principle; pulsed neural network approach; signal-dependent dictionary elements; spectrotemporal receptive field; Artificial neural networks; Dictionaries; Intelligent networks; Neural networks; Signal processing; Signal to noise ratio; Speech analysis; Speech enhancement; Speech processing; Time frequency analysis;
Conference_Titel :
Neural Networks for Signal Processing, 2003. NNSP'03. 2003 IEEE 13th Workshop on
Print_ISBN :
0-7803-8177-7
DOI :
10.1109/NNSP.2003.1318061
