Title :
Binding of audio elements in the sound source segregation problem via a two-layered bio-inspired neural network
Author :
Pichevar, Ramin ; Rouat, Jean
Author_Institution :
GEGI, Univ. de Sherbrooke, Que., Canada
Abstract :
We use a two-layered bio-inspired neural network to segregate sound sources, i.e. double-vowels or intruding noises in speech. The architecture of the network consists of spiking neurons. The spiking neurons in both layers are modelized by relaxation oscillators. The first layer of the network is locally connected, while the second layer is a fully connected network. Our auditory image is based on the reassigned spectrum technique. No prior estimation or knowledge of pitch is necessary for the segregation.
Keywords :
neural nets; relaxation oscillators; speech processing; auditory image; cochleotopic-AMtopic maps; cocktail-party effect; computational auditory scene analysis; double-vowels; reassigned spectrum technique; relaxation oscillators; sound source segregation; two-layered bio-inspired neural network; Biological neural networks; Humans; Image analysis; Independent component analysis; Intelligent networks; Layout; Neural networks; Neurons; Psychology; Speech;
Conference_Titel :
Electrical and Computer Engineering, 2003. IEEE CCECE 2003. Canadian Conference on
Print_ISBN :
0-7803-7781-8
DOI :
10.1109/CCECE.2003.1226101