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

You might also read

Related Articles

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

Sort by
Same author

Golden eagle based improved Att-BiLSTM model for big data classification with hybrid feature extraction and feature selection techniques.

Network (Bristol, England)·2023
Same author

Carbon Nanotube/Boron Nitride Nanocomposite as a Significant Bifunctional Electrocatalyst for Oxygen Reduction and Oxygen Evolution Reactions.

Chemistry (Weinheim an der Bergstrasse, Germany)·2016
See all related articles

Related Experiment Video

Updated: Apr 19, 2026

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

2.1K

Enhancing speech recognition using improved particle swarm optimization based hidden Markov model.

Lokesh Selvaraj1, Balakrishnan Ganesan2

  • 1Department of Computer Science & Engineering, Hindusthan Institute of Technology, Coimbatore, Tamil Nadu 641 032, India.

Thescientificworldjournal
|December 6, 2014
PubMed
Summary
This summary is machine-generated.

This study introduces a novel speech recognition method using vector quantization and improved particle swarm optimization (IPSO). The technique achieves high accuracy by integrating denoising, feature extraction, and an IPSO-based hidden Markov model (HMM).

More Related Videos

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

1.1K
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

1.3K

Related Experiment Videos

Last Updated: Apr 19, 2026

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

2.1K
Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

1.1K
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

1.3K

Area of Science:

  • Artificial Intelligence
  • Signal Processing
  • Computational Linguistics

Background:

  • Accurate speech recognition is crucial for human-computer interaction.
  • Existing methods face challenges with noise and complex feature extraction.
  • Optimization algorithms can enhance the performance of speech recognition models.

Purpose of the Study:

  • To propose a novel speech recognition method.
  • To enhance speech recognition accuracy using vector quantization and improved particle swarm optimization (IPSO).
  • To integrate denoising, feature extraction, vector quantization, and IPSO-based hidden Markov model (HMM) for improved performance.

Main Methods:

  • Speech signals were denoised using a median filter.
  • Key features including Mel frequency Cepstral coefficients (MFCC) were extracted.
  • Vector quantization with genetic algorithm-based codebook generation was employed.
  • Recognition was performed using an IPSO-based hidden Markov model (IP-HMM).

Main Results:

  • The proposed method achieved a high accuracy rate of 97.14%.
  • The integration of IPSO and HMM demonstrated effectiveness in speech recognition.
  • The multi-stage approach, including denoising and feature extraction, contributed to the accuracy.

Conclusions:

  • The novel speech recognition technique integrating vector quantization and IPSO offers superior performance.
  • The proposed IP-HMM method is a promising approach for enhancing speech recognition systems.
  • This methodology provides a robust framework for accurate speech signal processing.