Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Precision Training Via Causal Machine Learning: Modeling Rating of Perceived Exertion in Professional Soccer Players.

International journal of sports physiology and performance·2025

Same author

Machine learning-based identification of key biotic and abiotic drivers of mineral weathering rate in a complex enhanced weathering experiment.

Open research Europe·2025

Same author

Who is WithMe? EEG features for attention in a visual task, with auditory and rhythmic support.

Frontiers in neuroscience·2025

Same author

An encoding framework for binarized images using hyperdimensional computing.

Frontiers in big data·2024

Same author

Co-learning synaptic delays, weights and adaptation in spiking neural networks.

Frontiers in neuroscience·2024

Same author

Missing Value Imputation of Wireless Sensor Data for Environmental Monitoring.

Sensors (Basel, Switzerland)·2024

Search research articles

Related Experiment Video

Updated: Aug 21, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

Extended liquid state machines for speech recognition.

Lucas Deckers¹, Ing Jyh Tsang¹, Werner Van Leekwijck¹

¹imec IDLab, Department of Computer Science, University of Antwerp, Antwerp, Belgium.

Frontiers in Neuroscience

|November 17, 2022

Summary

This summary is machine-generated.

The extended liquid state machine (ELSM) enhances a liquid state machine (LSM) with bio-inspired features, improving speech recognition accuracy and efficiency. This biologically plausible model offers a hardware-friendly approach to spiking neural networks.

Keywords:

E/I balance liquid state machine neuronal diversity reservoir computing sound processing spike-frequency adaptation spiking neural networks

More Related Videos

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Published on: January 5, 2024

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Related Experiment Videos

Last Updated: Aug 21, 2025

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Author Spotlight: Advancements in the Fabrication of Synthetic Vocal Fold Models for Phonetic and Robotic Applications

Published on: January 5, 2024

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Area of Science:

Computational Neuroscience
Artificial Intelligence

Background:

Liquid State Machines (LSMs) are biologically plausible models of cortical microcircuits, known for their low training complexity and backpropagation-free learning.
Traditional LSMs utilize fixed synapses and a trainable readout layer for computation.

Purpose of the Study:

To enhance the Liquid State Machine (LSM) model with bio-inspired extensions, creating the Extended Liquid State Machine (ELSM).
To evaluate the ELSM's performance on speech datasets, focusing on improvements in accuracy, efficiency, and hardware compatibility.

Main Methods:

Implementing excitatory/inhibitory (E/I) balance to operate the LSM at the edge of chaos.
Introducing spike-frequency adaptation (SFA) to enhance memory capabilities.
Incorporating neuronal heterogeneity through differentiated time constants for richer dynamical responses.

Main Results:

The ELSM consistently outperformed the standard LSM, achieving up to a 5.2% increase in accuracy.
The number of spikes decreased by up to 20.2% in the ELSM, indicating improved efficiency.
ELSM demonstrated near state-of-the-art performance on speech recognition benchmarks and maintained performance with 4-bit synaptic weight resolution.

Conclusions:

The ELSM represents a powerful, biologically plausible, and hardware-friendly spiking neural network.
The bio-inspired extensions (E/I balance, SFA, neuronal heterogeneity) significantly improve LSM performance without compromising its core advantages.
ELSM shows promise for efficient and accurate speech recognition applications using spiking neural networks.