Conjoint Audio-to-Spikes Encoding and Processing for Efficient Neuromorphic Speech Recognition
2026-08-31 • Neural and Evolutionary Computing
Neural and Evolutionary ComputingArtificial IntelligenceMachine Learning
AI summaryⓘ
The authors explored a way to turn sound data into spikes that brain-like computers, called Spiking Neural Networks, can understand and process efficiently. They designed a simple, programmable encoder that works well on digital hardware and measured how well it performs without depending on specific devices. By improving both the encoding and the network that classifies the data, they achieved high accuracy while using less energy. Their approach was tested on standard speech and digit datasets and showed better results than previous methods. This work highlights a practical step towards hardware-friendly neuromorphic audio processing.
Neuromorphic sensorsSpiking Neural NetworksSpike encodingFPGAAudio classificationTIMIT datasetHeidelberg DigitsFeedforward networkEnergy-efficient AINeuromorphic computing
Authors
Valentin M. Meunier, Amélie Gruel, Pierre Lewden, Adrien F. Vincent, Sylvain Saïghi
Abstract
Obtaining data from neuromorphic sensors and processing it with Spiking Neural Networks is a promising solution to lower the energy cost of artificial intelligence. The current rarity of natively neuromorphic datasets promotes the development of software tools to translate input sensory data into spikes. However, highly bio-mimetic simulators can be challenging to implement on digital hardware. In this work, we evaluate the neuromorphic encoding and subsequent classification of audio into spikes using a non-learnable, high-level, programmable encoder targeting hardware implementation on FPGA. We quantify the pipeline's efficiency with hardware-agnostic metrics based on the quantitative spiking activity. Our study focuses on the simultaneous optimisation of encoder and classifier: the first provides efficient and informative data so that the latter achieves a better performance with an overall lower energy cost at learning and inference. This work introduces the first end-to-end neuromorphic spike-encoding and evaluation of the TIMIT dataset. Our simple feedforward network reaches a classification accuracy of 99.77% on a spike-encoded Heidelberg Digits, overcoming the neuromorphic state of the art on this benchmark dataset.