Monophonic sound source separation with an unsupervised network of spiking neurones

Authors:
Ramin Pichevar;Jean Rouat
Affiliations:
Département de génie électrique et génie informatique, Université de Sherbrooke, 2500 boul. de l'Université, Sherbrooke, Qué., Canada J1K 2R1;Département de génie électrique et génie informatique, Université de Sherbrooke, 2500 boul. de l'Université, Sherbrooke, Qué., Canada J1K 2R1
Venue:
Neurocomputing
Year:
2007

Citing 16
Cited 1

A neural cocktail-party processor

Biological Cybernetics
A pitch determination and voiced/unvoiced decision algorithm for noisy speech

Speech Communication
Image segmentation based on oscillatory correlation

Neural Computation
Computational auditory scene analysis

Computational auditory scene analysis
Robust automatic speech recognition with missing and unreliable acoustic data

Speech Communication
Spiking Neuron Models: An Introduction

Spiking Neuron Models: An Introduction
A theory and computational model of auditory monaural sound separation (stream, speech enhancement, selective attention, pitch perception, noise cancellation)

A theory and computational model of auditory monaural sound separation (stream, speech enhancement, selective attention, pitch perception, noise cancellation)
Prediction-driven computational auditory scene analysis

Prediction-driven computational auditory scene analysis
ARTSTREAM: a neural network model of auditory scene analysis and source segregation

Neural Networks
A maximum likelihood approach to single-channel source separation

The Journal of Machine Learning Research
On speech coding in a perceptual domain

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 01
Joint acoustic and modulation frequency

EURASIP Journal on Applied Signal Processing
Source separation with one ear: proposition for an anthropomorphic approach

EURASIP Journal on Applied Signal Processing
Separation of speech from interfering sounds based on oscillatory correlation

IEEE Transactions on Neural Networks
Unsupervised clustering with spiking neurons by sparse temporal coding and multilayer RBF networks

IEEE Transactions on Neural Networks
Monaural speech segregation based on pitch tracking and amplitude modulation

IEEE Transactions on Neural Networks

2013 Special Issue: Event management for large scale event-driven digital hardware spiking neural networks

Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

We incorporate auditory-based features into an unconventional pattern classification system, consisting of a network of spiking neurones with dynamical and multiplicative synapses. Although the network does not need any training and is autonomous, the analysis is dynamic and capable of extracting multiple features and maps. The neural network allows computing a binary mask that acts as a dynamic switch on a speech vocoder made of an FIR gammatone analysis/synthesis bank of 256 filters. We report experiments on separation of speech from various intruding sounds (siren, telephone bell, speech, etc.) and compare our approach to other techniques by using the log spectral distortion (LSD) metric.