A Spiking Neural Network Framework for Robust Sound Classification

  title={A Spiking Neural Network Framework for Robust Sound Classification},
  author={Jibin Wu and Yansong Chua and Malu Zhang and Haizhou Li and Kay Chen Tan},
  journal={Frontiers in Neuroscience},
Environmental sounds form part of our daily life. With the advancement of deep learning models and the abundance of training data, the performance of automatic sound classification (ASC) systems has improved significantly in recent years. However, the high computational cost, hence high power consumption, remains a major hurdle for large-scale implementation of ASC systems on mobile and wearable devices. Motivated by the observations that humans are highly effective and consume little power… 

Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition

This work uses SNNs for acoustic modeling and evaluates their performance on several large vocabulary recognition scenarios, demonstrating competitive ASR accuracies to their ANN counterparts while require only 10 algorithmic time steps and as low as 0.68 times total synaptic operations to classify each audio frame.

A Bin Encoding Training of a Spiking Neural Network Based Voice Activity Detection

This work develops a SNN-based Voice Activity Detection (VAD) system that belongs to the building blocks of any audio and speech processing system and shows that SNNs enable an ultra low-0power implementation of a VAD classifier that consumes only 3.8 µW, while achieving state-of-the-art performance.

Using a Low-Power Spiking Continuous Time Neuron (SCTN) for Sound Signal Processing

A new connectivity approach applied to Spiking Neuron (SN)-based neural networks, which allows referring to the basic SCTN as an analog module enabling the design of simple analog circuits based on SNN with unique inter-connections between the neurons.

A Tandem Learning Rule for Efficient and Rapid Inference on Deep Spiking Neural Networks.

The spike count is considered as the discrete neural representation and design ANN neuronal activation function that can effectively approximate the spike count of the coupled SNN in a tandem learning framework that consists of a SNN and an Artificial Neural Network that share weights.

Competitive STDP-based Feature Representation Learning for Sound Event Classification

A biologically plausible SEC system, which integrates the auditory front-end, population coding, competitive spike-timing-dependent plasticity (STDP) based feature representation learning and supervised temporal classification into a unified spiking neural network (SNN) system, achieves a classification accuracy on the RWCP database that is on par with other competitive baseline systems.

A Hybrid Learning Rule for Efficient and Rapid Inference with Spiking Neural Networks

A novel learning rule is proposed based on the hybrid neural network with shared weights, wherein a rate-based SNN is used during the forward propagation to determine precise spike counts and spike trains, and an equivalent ANN is used During error backpropagation to approximate the gradients for the coupled SNN.

Neural Population Coding for Effective Temporal Classification

It is shown that, with population neural coding, the encoded patterns are linearly separable using the Support Vector Machine (SVM), thus improving linear separability of the patterns.

Deep Spiking Neural Network with Spike Count based Learning Rule

A novel spike-based learning rule for rate-coded deep SNNs, whereby the spike count of each neuron is used as a surrogate for gradient backpropagation is introduced, which allows direct deployment to the neuromorphic hardware and supports efficient inference.

Automated Adaptive Threshold-Based Feature Extraction and Learning for Spiking Neural Networks

  • H. Amin
  • Computer Science
    IEEE Access
  • 2021
A new SNN-based model named Adaptive Threshold Module (ATM) and its algorithm that can make SNN provide an accuracy surpassing that of the current state-of-the-art SNN algorithms and conventional non-spiking learning models is proposed.



A Biologically Plausible Speech Recognition Framework Based on Spiking Neural Networks

This work proposes a biologically plausible speech recognition mechanism using unsupervised self-organizing map (SOM) for feature representation and event-driven spiking neural network (SNN) for spatiotemporal pattern classification that can be implemented using the artificial silicon cochlear and neuromorphic processor.

Bio-inspired Multi-layer Spiking Neural Network Extracts Discriminative Features from Speech Signals

This paper develops a bio-inspired SNN that uses unsupervised learning to extract discriminative features from speech signals, which can subsequently be used in a classifier that compares favorably with popular statistical feature extraction methods.

Feature Representations for Neuromorphic Audio Spike Streams

This work investigates the effectiveness of synchronous and asynchronous frame-based features generated using spike count and constant event binning in combination with the use of a recurrent neural network for solving a classification task using N-TIDIGITS18 dataset and proposes a new pre-processing method which applies an exponential kernel on the output cochlea spikes so that the interspike timing information is better preserved.

A Spiking Neural Network Model for Sound Recognition

A time-frequency encoding method which can retain the adequate information of original sound and generate spikes from represented features and train the SNN model with plausible supervised synaptic learning rule to efficiently perform various classification tasks is presented.

Training Deep Spiking Neural Networks Using Backpropagation

A novel technique is introduced, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise, which enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membranes potentials.

Robust Sound Event Classification Using Deep Neural Networks

A sound event classification framework is outlined that compares auditory image front end features with spectrogram image-based frontEnd features, using support vector machine and deep neural network classifiers, and is shown to compare very well with current state-of-the-art classification techniques.

Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks

A spatio-temporal backpropagation (STBP) algorithm for training high-performance SNNs is proposed, which combines the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD), and does not require any additional complicated skill.

Temporal coding of local spectrogram features for robust sound recognition

A novel approach based on the temporal coding of Local Spectrogram Features (LSFs), which generate spikes that are used to train a Spiking Neural Network (SNN) with temporal learning, able to outperform the conventional frame-based baseline methods.

Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines

An event-driven random backpropagation (eRBP) rule is demonstrated that uses an error-modulated synaptic plasticity rule for learning deep representations in neuromorphic computing hardware, achieving nearly identical classification accuracies compared to artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning.