Towards efficient end-to-end speech recognition with
biologically-inspired neural networks
- URL: http://arxiv.org/abs/2110.02743v1
- Date: Mon, 4 Oct 2021 21:24:10 GMT
- Title: Towards efficient end-to-end speech recognition with
biologically-inspired neural networks
- Authors: Thomas Bohnstingl, Ayush Garg, Stanis{\l}aw Wo\'zniak, George Saon,
Evangelos Eleftheriou and Angeliki Pantazi
- Abstract summary: We introduce neural connectivity concepts emulating the axo-somatic and the axo-axonic synapses.
We demonstrate for the first time, that a biologically realistic implementation of a large-scale ASR model can yield competitive performance levels.
- Score: 10.457580011403289
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Automatic speech recognition (ASR) is a capability which enables a program to
process human speech into a written form. Recent developments in artificial
intelligence (AI) have led to high-accuracy ASR systems based on deep neural
networks, such as the recurrent neural network transducer (RNN-T). However, the
core components and the performed operations of these approaches depart from
the powerful biological counterpart, i.e., the human brain. On the other hand,
the current developments in biologically-inspired ASR models, based on spiking
neural networks (SNNs), lag behind in terms of accuracy and focus primarily on
small scale applications. In this work, we revisit the incorporation of
biologically-plausible models into deep learning and we substantially enhance
their capabilities, by taking inspiration from the diverse neural and synaptic
dynamics found in the brain. In particular, we introduce neural connectivity
concepts emulating the axo-somatic and the axo-axonic synapses. Based on this,
we propose novel deep learning units with enriched neuro-synaptic dynamics and
integrate them into the RNN-T architecture. We demonstrate for the first time,
that a biologically realistic implementation of a large-scale ASR model can
yield competitive performance levels compared to the existing deep learning
models. Specifically, we show that such an implementation bears several
advantages, such as a reduced computational cost and a lower latency, which are
critical for speech recognition applications.
Related papers
- Enhancing learning in artificial neural networks through cellular heterogeneity and neuromodulatory signaling [52.06722364186432]
We propose a biologically-informed framework for enhancing artificial neural networks (ANNs)
Our proposed dual-framework approach highlights the potential of spiking neural networks (SNNs) for emulating diverse spiking behaviors.
We outline how the proposed approach integrates brain-inspired compartmental models and task-driven SNNs, bioinspiration and complexity.
arXiv Detail & Related papers (2024-07-05T14:11:28Z) - Exploring neural oscillations during speech perception via surrogate gradient spiking neural networks [59.38765771221084]
We present a physiologically inspired speech recognition architecture compatible and scalable with deep learning frameworks.
We show end-to-end gradient descent training leads to the emergence of neural oscillations in the central spiking neural network.
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.
arXiv Detail & Related papers (2024-04-22T09:40:07Z) - Single Neuromorphic Memristor closely Emulates Multiple Synaptic
Mechanisms for Energy Efficient Neural Networks [71.79257685917058]
We demonstrate memristive nano-devices based on SrTiO3 that inherently emulate all these synaptic functions.
These memristors operate in a non-filamentary, low conductance regime, which enables stable and energy efficient operation.
arXiv Detail & Related papers (2024-02-26T15:01:54Z) - Astrocyte-Enabled Advancements in Spiking Neural Networks for Large
Language Modeling [7.863029550014263]
Astrocyte-Modulated Spiking Neural Network (AstroSNN) exhibits exceptional performance in tasks involving memory retention and natural language generation.
AstroSNN shows low latency, high throughput, and reduced memory usage in practical applications.
arXiv Detail & Related papers (2023-12-12T06:56:31Z) - Brain-Inspired Machine Intelligence: A Survey of
Neurobiologically-Plausible Credit Assignment [65.268245109828]
We examine algorithms for conducting credit assignment in artificial neural networks that are inspired or motivated by neurobiology.
We organize the ever-growing set of brain-inspired learning schemes into six general families and consider these in the context of backpropagation of errors.
The results of this review are meant to encourage future developments in neuro-mimetic systems and their constituent learning processes.
arXiv Detail & Related papers (2023-12-01T05:20:57Z) - A Hybrid Neural Coding Approach for Pattern Recognition with Spiking
Neural Networks [53.31941519245432]
Brain-inspired spiking neural networks (SNNs) have demonstrated promising capabilities in solving pattern recognition tasks.
These SNNs are grounded on homogeneous neurons that utilize a uniform neural coding for information representation.
In this study, we argue that SNN architectures should be holistically designed to incorporate heterogeneous coding schemes.
arXiv Detail & Related papers (2023-05-26T02:52:12Z) - Developmental Plasticity-inspired Adaptive Pruning for Deep Spiking and
Artificial Neural Networks [7.000088703181348]
Developmental plasticity plays a vital role in shaping the brain's structure during ongoing learning.
Existing network compression methods for deep artificial neural networks (ANNs) and spiking neural networks (SNNs) draw little inspiration from the brain's developmental plasticity mechanisms.
This paper proposes a developmental plasticity-inspired adaptive pruning (DPAP) method, with inspiration from the adaptive developmental pruning of dendritic spines, synapses, and neurons.
arXiv Detail & Related papers (2022-11-23T05:26:51Z) - A brain basis of dynamical intelligence for AI and computational
neuroscience [0.0]
More brain-like capacities may demand new theories, models, and methods for designing artificial learning systems.
This article was inspired by our symposium on dynamical neuroscience and machine learning at the 6th Annual US/NIH BRAIN Initiative Investigators Meeting.
arXiv Detail & Related papers (2021-05-15T19:49:32Z) - Deep learning approaches for neural decoding: from CNNs to LSTMs and
spikes to fMRI [2.0178765779788495]
Decoding behavior, perception, or cognitive state directly from neural signals has applications in brain-computer interface research.
In the last decade, deep learning has become the state-of-the-art method in many machine learning tasks.
Deep learning has been shown to be a useful tool for improving the accuracy and flexibility of neural decoding across a wide range of tasks.
arXiv Detail & Related papers (2020-05-19T18:10:35Z) - Recurrent Neural Network Learning of Performance and Intrinsic
Population Dynamics from Sparse Neural Data [77.92736596690297]
We introduce a novel training strategy that allows learning not only the input-output behavior of an RNN but also its internal network dynamics.
We test the proposed method by training an RNN to simultaneously reproduce internal dynamics and output signals of a physiologically-inspired neural model.
Remarkably, we show that the reproduction of the internal dynamics is successful even when the training algorithm relies on the activities of a small subset of neurons.
arXiv Detail & Related papers (2020-05-05T14:16:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.