End-to-End Spiking Neural Network for Speech Recognition Using Resonating Input Neurons

Auge, Daniel; Hille, Julian; Kreutz, Felix; Mueller, Etienne; Knoll, Alois

doi:10.1007/978-3-030-86383-8_20

Cited by 10 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the neuron model only works with real values, the complex matrix B 4x4 • W 4x4 is transformed into a real-valued 8-by-8 radix-4 matrix W 8x8 •B 8x8 , where half of the connections represent the imaginary components. By using the same rephrasing as in (9), the transformation yields the result…”

Section: Spiking Fast Fourier Transformationmentioning

confidence: 99%

“…Along with the continuous improvement of neuromorphic chips, SNN-based solutions have emerged in recent years for various applications and sensors, ranging from speech recognition with resonate-and-fire neurons [9], object tracking for monocular vision [10,11], object detection using raw temporal pulses of lidar sensors [12] for lane keeping Time-coded spiking FT [13], feature extraction and motion perception [14], and collision avoidance based on data obtained from a dynamic vision sensor [15]. Currently, the most prominent task addressed in radar data processing using SNNs is gesture recognition [16,17,18,19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Time-coded Spiking Fourier Transform in Neuromorphic Hardware

López-Randulfe,

Reeb,

Karimi

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

After several decades of continuously optimizing computing systems, the Moore's law is reaching its end. However, there is an increasing demand for fast and efficient processing systems that can handle large streams of data while decreasing system footprints. Neuromorphic computing answers this need by creating decentralized architectures that communicate with binary events over time. Despite its rapid growth in the last few years, novel algorithms are needed that can leverage the potential of this emerging computing paradigm and can stimulate the design of advanced neuromorphic chips. In this work, we propose a time-based spiking neural network that is mathematically equivalent to the Fourier transform. We implemented the network in the neuromorphic chip Loihi and conducted experiments on five different real scenarios with an automotive frequency modulated continuous wave radar. Experimental results validate the algorithm, and we hope they prompt the design of ad hoc neuromorphic chips that can improve the efficiency of state-of-the-art digital signal processors and encourage research on neuromorphic computing for signal processing.

show abstract

Section: Spiking Fast Fourier Transformationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Time-coded Spiking Fourier Transform in Neuromorphic Hardware

López-Randulfe,

Reeb,

Karimi

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A spike is generated as soon as the second variable x 2 reaches the firing threshold. The spike pattern of an RF neuron contains information about the frequency, amplitude, phase, and their temporal development in the analyzed signal (Auge et al, 2021a).…”

Section: Resonate-and-fire Neuronsmentioning

confidence: 99%

Automotive Radar Processing With Spiking Neural Networks: Concepts and Challenges

et al. 2022

Self Cite

View full text Add to dashboard Cite

Frequency-modulated continuous wave radar sensors play an essential role for assisted and autonomous driving as they are robust under all weather and light conditions. However, the rising number of transmitters and receivers for obtaining a higher angular resolution increases the cost for digital signal processing. One promising approach for energy-efficient signal processing is the usage of brain-inspired spiking neural networks (SNNs) implemented on neuromorphic hardware. In this article we perform a step-by-step analysis of automotive radar processing and argue how spiking neural networks could replace or complement the conventional processing. We provide SNN examples for two processing steps and evaluate their accuracy and computational efficiency. For radar target detection, an SNN with temporal coding is competitive to the conventional approach at a low compute overhead. Instead, our SNN for target classification achieves an accuracy close to a reference artificial neural network while requiring 200 times less operations. Finally, we discuss the specific requirements and challenges for SNN-based radar processing on neuromorphic hardware. This study proves the general applicability of SNNs for automotive radar processing and sustains the prospect of energy-efficient realizations in automated vehicles.

show abstract

“…We refer the interested reader to [29] for getting an overview of the different analog circuits used in neuromorphic systems for real-time applications, and to [30] for a comparison of the different encoding approaches. Some neuromorphic applications focus on generating the frequency spectrum of the incoming signal [24,31,32]. In these examples, an analog-to-digital converter (ADC) samples the sensor data and an SNN computes a higher-level algorithm on a digital neuromorphic chip afterward.…”

Section: Introductionmentioning

confidence: 99%

“…This is the case of embedded systems where the pool of energy is limited, such as automotive applications [20,21]. There are recent examples of neuromorphic computing algorithms that deal with low-end tasks and are applied to sensor data, such as LiDAR [20], event-based cameras [22], FMCW radar [21], electrocardiogram signals [23], or microphones [24].…”

Section: Introductionmentioning

confidence: 99%

Integrate-and-fire circuit for converting analog signals to spikes using phase encoding ^*

Lopez-Randulfe,

Reeb,

Knoll

2023

Neuromorph. Comput. Eng.

Self Cite

View full text Add to dashboard Cite

Processing sensor data with spiking neural networkson digital neuromorphic chips requires converting continuousanalog signals into spike pulses. Two strategies are promising forachieving low energy consumption and fast processing speeds inend-to-end neuromorphic applications. First, to directly encodeanalog signals to spikes to bypass the need for an analog-to-digitalconverter (ADC). Second, to use temporal encoding techniquesto maximize the spike sparsity, which is a crucial parameterfor fast and efficient neuromorphic processing. In this work, wepropose an adaptive control of the refractory period of the leakyintegrate-and-fire (LIF) neuron model for encoding continuousanalog signals into a train of time-coded spikes. The LIF-basedencoder generates phase-encoded spikes that are compatiblewith digital hardware. We implemented the neuron model ona physical circuit and tested it with different electric signals. Adigital neuromorphic chip processed the generated spike trainsand computed the signal’s frequency spectrum using a spikingversion of the Fourier transform. We tested the prototype circuiton electric signals up to 1 KHz. Thus, we provide an end-to-endneuromorphic application that generates the frequency spectrumof an electric signal without the need for an ADC or a digitalsignal processing algorithm.

show abstract

End-to-End Spiking Neural Network for Speech Recognition Using Resonating Input Neurons

Cited by 10 publications

References 18 publications

Time-coded Spiking Fourier Transform in Neuromorphic Hardware

Time-coded Spiking Fourier Transform in Neuromorphic Hardware

Automotive Radar Processing With Spiking Neural Networks: Concepts and Challenges

Integrate-and-fire circuit for converting analog signals to spikes using phase encoding ^*

Contact Info

Product

Resources

About

End-to-End Spiking Neural Network for Speech Recognition Using Resonating Input Neurons

Cited by 10 publications

References 18 publications

Time-coded Spiking Fourier Transform in Neuromorphic Hardware

Time-coded Spiking Fourier Transform in Neuromorphic Hardware

Automotive Radar Processing With Spiking Neural Networks: Concepts and Challenges

Integrate-and-fire circuit for converting analog signals to spikes using phase encoding *

Contact Info

Product

Resources

About

Integrate-and-fire circuit for converting analog signals to spikes using phase encoding ^*