Binding of audio elements in the sound source segregation problem via a two-layered bio-inspired neural network

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.

[1]  Daniel P. W. Ellis,et al.  The auditory organization of speech and other sources in listeners and computational models , 2001, Speech Commun..

[2]  Jean Rouat,et al.  Double-vowel segregation through temporal correlation: a bio-inspired neural network paradigm , 2003, NOLISP.

[3]  T. Poggio,et al.  Are Cortical Models Really Bound by the “Binding Problem”? , 1999, Neuron.

[4]  Fabrice Plante,et al.  Improvement of speech spectrogram accuracy by the method of reassignment , 1998, IEEE Trans. Speech Audio Process..

[5]  Jean Rouat,et al.  Nonlinear speech processing with oscillatory neural networks for speaker segregation , 2002, 2002 11th European Signal Processing Conference.

[6]  C. von der Malsburg.  The what and why of binding: the modeler's perspective. , 1999, Neuron.

[7]  R. Desimone,et al.  The Role of Neural Mechanisms of Attention in Solving the Binding Problem , 1999, Neuron.

[8]  Guy J. Brown,et al.  Separation of speech from interfering sounds based on oscillatory correlation , 1999, IEEE Trans. Neural Networks.

[9]  DeLiang Wang,et al.  Image Segmentation Based on Oscillatory Correlation , 1997, Neural Computation.

[10]  DeLiang Wang,et al.  Fast numerical integration of relaxation oscillator networks based on singular limit solutions , 1998, IEEE Trans. Neural Networks.

[11]  P. S. Lindsey,et al.  Fast numerical integration of relaxation oscillator networks based on singular limit solutions , 1996 .

[12]  Eduardo D. Sontag,et al.  Neural Systems as Nonlinear Filters , 2000, Neural Computation.

[13]  Ch. von der Malsburg,et al.  A neural cocktail-party processor , 1986, Biological Cybernetics.

[14]  Wolfgang Konen,et al.  A fast dynamic link matching algorithm for invariant pattern recognition , 1994, Neural Networks.

[15]  N. Todd,et al.  An auditory cortical theory of primitive auditory grouping. , 1996, Network.