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

Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

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

Sort by
Same author

An Explainable AI-Based Transfer Learning Method for Breast Cancer Prediction.

Journal of visualized experiments : JoVE·2026
Same author

BEML-sonar: a bio-inspired echolocation and machine learning-enhanced SONAR for underwater object detection and navigation.

Scientific reports·2026
Same author

Language-assisted multimodal convolutional transformer pipeline for retinal lesions segmentation.

Scientific reports·2026
Same author

Building novel LLM-enabled explainable ensemble transformer models combining endoscopic and CT images for discriminating the different grades of gastrointestinal cancers.

Frontiers in medicine·2026
Same author

Time series electrocardiography (ECG) data for early prediction of cardiac arrest.

Scientific reports·2026
Same author

Intelligent web archiving and ranking of fake news using metadata-driven credibility assessment and machine learning.

Scientific reports·2025

Related Experiment Video

Updated: May 22, 2026

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

An Edge-Enabled Low-Latency Cross-Lingual Speech-to-Text Framework for Efficient Human-Robot Interaction.

Abdullah Albuali1, Nishant Tripathi2, Mahesh T R2

  • 1Department of Computer Networks, College of Computer Science and Information Technology, King Faisal University, Dammam, Al Ahsa, Saudi Arabia.

Big Data
|May 21, 2026
PubMed
Summary

This study introduces an edge-centric speech-to-text framework for multilingual humanoid robots. It significantly reduces latency and improves reliability by processing speech onboard, enhancing human-robot interaction.

Keywords:
cross-lingual speech recognitionhumanoid robotslow-latency STTreal-time interactionwireless edge networks

Related Experiment Videos

Last Updated: May 22, 2026

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

Area of Science:

  • Robotics
  • Artificial Intelligence
  • Natural Language Processing

Background:

  • Humanoid robots require natural, low-latency speech interaction in multilingual environments.
  • Current cloud-based speech-to-text systems suffer from latency, connectivity issues, and unreliability for real-time robot applications.

Purpose of the Study:

  • To develop an edge-centric speech-to-text framework for multilingual humanoid robots.
  • To overcome the limitations of cloud-based systems in real-time human-robot communication.

Main Methods:

  • Implemented lightweight neural models for real-time streaming speech processing on the robot.
  • Developed an onboard mechanism for real-time language identification.
  • Utilized local caching for efficient retrieval of speech patterns.

Main Results:

  • Achieved over 60% reduction in overall response time compared to cloud-based systems.
  • Demonstrated robust performance with fluctuating network conditions, packet loss, and background noise.
  • Enabled quicker, more trustworthy, and multilingual speech transcription.

Conclusions:

  • Edge-based, multilingual speech-to-text systems are crucial for enhancing humanoid robot responsiveness and contextuality.
  • This framework facilitates smoother conversations and more natural human-robot interactions.
  • Onboard speech processing is key to pragmatic and reliable communication in real-world robotic applications.