Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks
Not on the map. Why?
Abstract (arXiv)
Understanding cognitive processes in the brain demands sophisticated models capable of replicating neural dynamics at large scales. We present a physiologically inspired speech recognition architecture, compatible and scalable with deep learning frameworks, and demonstrate that end-to-end gradient descent training leads to the emergence of neural oscillations in the central spiking neural network. Significant cross-frequency couplings, indicative of these oscillations, are measured within and across network layers during speech processing, whereas no such interactions are observed when handling background noise inputs. Furthermore, our findings highlight the crucial inhibitory role of feedback mechanisms, such as spike frequency adaptation and recurrent connections, in regulating and synchronising neural activity to improve recognition performance. Overall, on top of developing our understanding of synchronisation phenomena notably observed in the human auditory pathway, our architecture exhibits dynamic and efficient information processing, with relevance to neuromorphic technology.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 17 of its 93 references that are in the map. First posted on arXiv 22 Apr 2024.
Builds on
17 of 93 references.
References · 17
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,004
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,870
- 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,844
- 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 748
- 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 617
- 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
- 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 180
- 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 114
- 2022Toward a realistic model of speech processing in the brain with self-supervised learningcited by 63
- 2021Scaling End-to-End Models for Large-Scale Multilingual ASRcited by 61
- 2023Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacingscited by 50
- 2019A scalable noisy speech dataset and online subjective test frameworkcited by 48
5 more
- 2020Effective and Efficient Computation with Multiple-timescale Spiking Recurrent Neural Networkscited by 43
- 2022Fluctuation-driven initialization for spiking neural network trainingcited by 16
- 2021Inductive biases, pretraining and fine-tuning jointly account for brain responses to speechcited by 14
- 2023Co-learning synaptic delays, weights and adaptation in spiking neural networkscited by 13
- 2022Surrogate Gradient Spiking Neural Networks as Encoders for Large Vocabulary Continuous Speech Recognitioncited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.