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 Experiment Videos

Human-like dynamic programming neural networks for dynamic time warping speech recognition

C Chiu1, M A Shanblatt

  • 1R&D Labs, Factory Automation Division, Sony Electronics Inc., Orangeburg, NY 10962, USA.

International Journal of Neural Systems
|March 1, 1995
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Risk analysis for outpatient experimental infection as a pathway for affordable RSV vaccine development.

NPJ vaccines·2025
Same author

Canadian Surgery Forum 2018: St. John's, NL Sept. 13-15, 2018.

Canadian journal of surgery. Journal canadien de chirurgie·2022
Same author

An artificial intelligence algorithm that differentiates anterior ethmoidal artery location on sinus computed tomography scans.

The Journal of laryngology and otology·2019
Same author

Chronic minocycline treatment improves hippocampal neuronal structure, NMDA receptor function, and memory processing in Fmr1 knockout mice.

Neurobiology of disease·2018
Same author

Investigating adverse events following immunisation with pneumococcal polysaccharide vaccine using electronic General Practice data.

Vaccine·2017
Same author

Impaired bidirectional NMDA receptor dependent synaptic plasticity in the dentate gyrus of adult female Fmr1 heterozygous knockout mice.

Neurobiology of disease·2016
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

This study introduces a novel neural network approach for speech recognition, mimicking human learning. This dynamic programming method with dynamic time warping significantly outperforms traditional techniques for word classification.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Signal Processing

Background:

  • Speech recognition systems often struggle with variability in human speech.
  • Conventional methods may lack the adaptability and efficiency of human-like processing.

Purpose of the Study:

  • To present a human-like dynamic programming neural network for enhanced speech recognition.
  • To analyze the dynamics and properties of these novel neural networks.
  • To demonstrate the method's superiority over existing approaches.

Main Methods:

  • Utilizing dynamic programming neural networks configured to minimize energy function states.
  • Employing dynamic time warping for pattern correlation.
  • Analytical explanation of network dynamics and properties.

Related Experiment Videos

Main Results:

  • Simulations show superior performance in classifying speaker-dependent isolated words (0-9, A-Z).
  • The method demonstrates better correlation between test and reference patterns.
  • Successful hardware implementation was achieved.

Conclusions:

  • The proposed human-like dynamic programming neural network offers a significant advancement in speech recognition.
  • The method provides a more efficient and accurate approach compared to conventional techniques.
  • The findings support the potential for practical hardware implementation.