Recognition of auditory objects from continuous and ultra-sparse spike streams in neuromorphic devices
Abstract
Energy consumption is a major concern for modern artificial intelligence (AI) applications. The brain is thought to achieve energy-efficient computation through sparse coding schemes. By emulating the spiking dynamics of the brain, neuromorphic chips hold the potential to realize energy-efficient AI. In this work, we use birdsong to demonstrate that auditory object recognition can be achieved using ultra-sparse coding. Feature-detecting neurons tuned to short temporal features (∼37 ms), sampled from exemplar syllables, transform continuous auditory signals into streams of ultra-sparse spikes that mark the onsets and offsets of features within the signal. Spike patterns elicited by the exemplars are stored as templates. During recognition, template matching is performed using axonal delays between feature-detecting and template-detecting neurons. Recognition is further enhanced by an additional group of specialized binary neurons trained to discriminate between syllable categories with subtle differences. When tested on Bengalese finch songs, our approach achieved error rates below 5% using 10 to 40 exemplars per syllable type. We then implemented this recognition algorithm using spiking neural networks on Intel's neuromorphic chip, Loihi, and found that response latencies remain constant (approximately 17 ms per syllable), regardless of the number of templates used. Our results demonstrate the potential of neuromorphic chips for low-latency, low-energy recognition of complex sounds, including speech.
Related
- Event-driven neuromorphic vision enables energy-efficient visual place recognition
- Divergent processing strategies for auditory sequence recognition in humans and zebra finches (Taeniopygia guttata)
- Bio-Inspired Auditory Processing: Coupling Parallel Resonate-and-Fire Dynamics with Ternary Recurrent Networks for Speech Recognition
- A Deep Neural Network for Predicting Continuous Human EEG Across the Auditory Pathway in Response to Sound
- What is neuromorphic about neuromorphic computing?
BibTeX
@misc{tavares2026recognition,
title = {{Recognition of auditory objects from continuous and ultra-sparse spike streams in neuromorphic devices}},
author = {Leonardo E. S. Tavares and Kevin D. Sargent and Jon T. Sakata and Dezhe Z. Jin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.38564},
eprint = {2610.38564},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.38564},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Recognition of auditory objects from continuous and ultra-sparse spike streams in neuromorphic devices
AU - Leonardo E. S. Tavares
AU - Kevin D. Sargent
AU - Jon T. Sakata
AU - Dezhe Z. Jin
PY - 2026
DA - 2026/10/28
PB - arXiv
DO - 10.48550/arxiv.2610.38564
UR - https://arxiv.org/abs/2610.38564
AB - Energy consumption is a major concern for modern artificial intelligence (AI) applications. The brain is thought to achieve energy-efficient computation through sparse coding schemes. By emulating the spiking dynamics of the brain, neuromorphic chips hold the potential to realize energy-efficient AI. In this work, we use birdsong to demonstrate that auditory object recognition can be achieved using ultra-sparse coding. Feature-detecting neurons tuned to short temporal features (∼37 ms), sampled from exemplar syllables, transform continuous auditory signals into streams of ultra-sparse spikes that mark the onsets and offsets of features within the signal. Spike patterns elicited by the exemplars are stored as templates. During recognition, template matching is performed using axonal delays between feature-detecting and template-detecting neurons. Recognition is further enhanced by an additional group of specialized binary neurons trained to discriminate between syllable categories with subtle differences. When tested on Bengalese finch songs, our approach achieved error rates below 5% using 10 to 40 exemplars per syllable type. We then implemented this recognition algorithm using spiking neural networks on Intel's neuromorphic chip, Loihi, and found that response latencies remain constant (approximately 17 ms per syllable), regardless of the number of templates used. Our results demonstrate the potential of neuromorphic chips for low-latency, low-energy recognition of complex sounds, including speech.
SN - 2331-8422
ER -