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

11.9K
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...
11.9K

You might also read

Related Articles

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

Sort by
Same author

Bone marrow mesenchymal stem cell-derived apoptotic bodies alleviate periodontitis-associated alveolar bone resorption by promoting osteogenesis.

Biochemical and biophysical research communications·2026
Same author

Changes in coronal sacral tilt angle following hemivertebrectomy in children with scoliosis due to congenital lumbar hemivertebra.

European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society·2026
Same author

Spatial Tail Design in Ionizable Lipids Enhances the Safety and Efficacy of mRNA Delivery.

Small methods·2026
Same author

Single-nucleus interrogation of primate small intestinal aging reveals NCoR1 decline as a conserved feature that is reversed by metformin.

Nature aging·2026
Same author

Structural mechanism of TopBP1 recognizing phosphorylated HTATSF1 in homologous recombination repair.

Biochemical and biophysical research communications·2026
Same author

Structural mechanism of diacetylated histone H2A recognition by Bromodomain-containing protein 4 in Regulation of non-homologous end-joining DNA repair.

International journal of biological macromolecules·2026

Related Experiment Video

Updated: Sep 16, 2025

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

1.6K

Evaluating Mandarin tone pronunciation accuracy for second language learners using a ResNet-based Siamese network.

Xiaolong Bu1, Weitong Guo2,3, Hongwu Yang4,5

  • 1School of Educational Technology, Northwest Normal University, Lanzhou, 730070, China.

Scientific Reports
|July 8, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces an automatic Mandarin tone pronunciation evaluation system using a Siamese network (SN). The system effectively identifies tone pronunciation errors for second-language (L2) learners by analyzing pitch contours.

More Related Videos

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
06:04

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

474
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K

Related Experiment Videos

Last Updated: Sep 16, 2025

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

1.6K
Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
06:04

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

474
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K

Area of Science:

  • Computational Linguistics
  • Speech Technology
  • Second Language Acquisition

Background:

  • Mastering Mandarin tones is crucial for second-language (L2) learners.
  • Current methods for evaluating tone pronunciation can be subjective and time-consuming.
  • There is a need for objective and automated tools to assess Mandarin tone accuracy.

Purpose of the Study:

  • To develop and evaluate an innovative automatic method for assessing Mandarin tone pronunciation.
  • To utilize a Siamese network (SN) for analyzing pitch contours and identifying tone discrepancies.
  • To provide L2 Mandarin learners with accurate feedback on their tone production.

Main Methods:

  • A specialized Mandarin speech corpus was created, including standard and non-standard accents.
  • Pitch contours were extracted, smoothed using Local Weighted Regression, and normalized to a 0-5 scale.
  • Two types of features were extracted: a 1D vector and a 2D image representation of the pitch contour.
  • A Siamese network was trained to compare paired tone features and detect pronunciation errors.
  • Experiments were conducted using various deep learning models (ResNet-18, VGG-16, AlexNet) and a baseline.

Main Results:

  • The proposed Siamese network method effectively assesses tone discrepancies in Mandarin pronunciation.
  • Both 1D and 2D features demonstrated compatibility with multiple models, with 2D features showing superior consistency with ResNet-18.
  • Subjective evaluations yielded a Mean Squared Error (MSE) of 2.295 and Root Mean Squared Error (RMSE) of 1.515.
  • Objective evaluations achieved an MSE of 0.189 and RMSE of 0.435.
  • ResNet-18 with 2D features proved particularly stable and effective.

Conclusions:

  • The developed automatic evaluation method accurately assesses Mandarin tone pronunciation discrepancies.
  • The Siamese network approach, particularly with 2D features and ResNet-18, offers a robust solution for L2 learners.
  • This research provides a foundation for advanced, automated tone evaluation systems for Mandarin learners.