Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Long-term Potentiation01:35

Long-term Potentiation

Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Long-term Potentiation01:25

Long-term Potentiation

Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Hebbian LTP
LTP can occur when presynaptic neurons...
Higher Mental Functions of Brain: Learning and Memory01:26

Higher Mental Functions of Brain: Learning and Memory

Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or playing an...
Chunking and Rehearsal in Sensory Memory01:22

Chunking and Rehearsal in Sensory Memory

Improving short-term memory can be achieved through techniques like chunking and rehearsal. Chunking involves organizing information into larger, more manageable units. This technique is particularly useful for information that exceeds the typical memory span of between five and nine items. For instance, logging into an online account with a password like "ta89vq0179gz" involves grouping letters and numbers into three chunks—ta89, vq01, and 79gz. It makes large amounts of information more...
Long-Term Memory01:18

Long-Term Memory

Long-term memory is a relatively permanent type of memory, capable of storing vast amounts of information over extended periods. Its storage capacity is generally considered unlimited.
Long-term memory can be categorized into two primary types: explicit and implicit memory. Explicit memory, also known as declarative memory, involves the conscious recollection of information that we deliberately try to remember, recall, and articulate. This type of memory encompasses specific facts, events, and...
Elaborative Rehearsals01:07

Elaborative Rehearsals

Elaborative rehearsal is a crucial cognitive strategy that strengthens information encoding in long-term memory by making meaningful connections between new data and pre-existing knowledge. This approach contrasts with maintenance rehearsal, which involves simple repetition without delving into the significance of the information. While maintenance rehearsal might temporarily keep information active in short-term memory, it is less effective for long-term retention.
The effectiveness of...

You might also read

Related Articles

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

Sort by
Same author

Compact ferroelectric domain-ensemble model linking PUND switching, wake-up, and plasmonic optical readout.

Optics express·2026
Same author

When Light Drives Discovery: Plasmonics at the Frontier of Energy Materials.

Chemistry of materials : a publication of the American Chemical Society·2026
Same author

An Oscillating-Flow Microfluidic PCR Method for Rapid and Flexible Detection of Periodontal Pathogens.

Sensors (Basel, Switzerland)·2026
Same author

A low-cost, high-throughput DNA quantification system using light pipe arrays for parallel fluorescence measurement.

Analytical methods : advancing methods and applications·2026
Same author

3D-ViT-UNet: 3D Vision transformer based Unet-like model for Volumetric Brain Tumor Segmentation.

PLOS digital health·2026
Same author

Parameter-Reduced YOLOv8n with GhostConv and C3Ghost for Automated Blood Cell Detection.

Bioengineering (Basel, Switzerland)·2026

Related Experiment Video

Updated: Jul 8, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

557

Deep causal speech enhancement and recognition using efficient long-short term memory Recurrent Neural Network.

Zhenqing Li1, Abdul Basit1, Amil Daraz1

  • 1School of Information Science and Engineering, NingboTech University, Ningbo, China.

Plos One
|January 3, 2024
PubMed
Summary

This study introduces an hourglass-shaped Long Short-Term Memory (LSTM) network to improve speech enhancement and recognition by capturing long-term temporal dependencies. The novel causal model significantly boosts speech intelligibility and quality while reducing word error rates in noisy conditions.

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

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

Published on: August 9, 2024

1.5K

Related Experiment Videos

Last Updated: Jul 8, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

557
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

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

Published on: August 9, 2024

1.5K

Area of Science:

  • Artificial Intelligence
  • Deep Learning
  • Speech Processing

Background:

  • Long Short-Term Memory (LSTM) networks are effective for sequential data but struggle with long-term dependencies.
  • Existing deep neural networks (DNNs) face challenges in accurately processing noisy speech for enhancement and recognition tasks.
  • Causality and real-time processing are critical requirements for practical speech applications.

Purpose of the Study:

  • To propose a novel hourglass-shaped LSTM architecture capable of capturing long-term temporal correlations in sequential data.
  • To enhance speech enhancement and recognition performance by improving feature representation and addressing gradient decay.
  • To develop a causal system suitable for real-time speech processing without relying on future information.

Main Methods:

  • Developed an hourglass-shaped LSTM architecture with reduced feature resolutions and skip connections to preserve information and prevent gradient decay.
  • Incorporated an attention mechanism into skip connections to emphasize critical spectral features and regions.
  • Trained the model using combined spectral feature sets and the ideal ratio mask (IRM) as a training objective for speech enhancement.

Main Results:

  • The proposed LSTM model achieved significant improvements in speech intelligibility (STOI) by up to 18.33% and perceptual quality (PESQ) by up to 32.9% across multiple datasets.
  • Outperformed existing DNNs, including baseline LSTM, FDNN, CNN, and GAN, in both seen and unseen noisy conditions.
  • Reduced word error rates (WERs) in automated speech recognition (ASR) tasks, achieving an average WER of 15.13% in noisy environments.

Conclusions:

  • The proposed hourglass-shaped LSTM with attention and skip connections effectively captures long-term temporal dependencies for robust speech processing.
  • The causal nature of the model makes it suitable for real-time applications, offering superior performance in speech enhancement and recognition.
  • This novel architecture represents a significant advancement in deep learning for handling noisy speech data, enhancing both intelligibility and recognition accuracy.