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

A statistics-based pitch contour model for Mandarin speech.

Sin-Horng Chen1, Wen-Hsing Lai, Yih-Ru Wang

  • 1Department of Communication Engineering, National Chiao Tung University, Taiwan.

The Journal of the Acoustical Society of America
|March 12, 2005
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

Forecast Padding Enhances Accuracy and Robustness of EEG-Phase-Synchronized TMS.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2025
Same author

Delay Analysis in Closed-Loop EEG Phase-Triggered Transcranial Magnetic Stimulation.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023
Same author

An approach to constructing prosodic grammar for Mandarin read speech.

The Journal of the Acoustical Society of America·2023
Same author

Hierarchical prosody modeling for Mandarin spontaneous speech.

The Journal of the Acoustical Society of America·2019
Same author

Unsupervised joint prosody labeling and modeling for Mandarin speech.

The Journal of the Acoustical Society of America·2009

This study introduces a statistical model for Mandarin speech pitch contours, analyzing factors like speaker and tone. The model accurately reconstructs pitch, offering new insights into speech variations and prosody.

Area of Science:

  • Speech processing
  • Computational linguistics
  • Acoustic phonetics

Background:

  • Accurate modeling of syllable pitch contours is crucial for speech synthesis and analysis.
  • Existing models often lack the ability to comprehensively account for multiple influencing factors.
  • Understanding prosodic variations in Mandarin speech requires robust statistical frameworks.

Purpose of the Study:

  • To propose a statistics-based model for Mandarin syllable pitch contours.
  • To identify and quantify the impact of key factors on pitch contour variations.
  • To provide a more detailed and quantitative analysis of coarticulation and prosodic phenomena.

Main Methods:

  • Developed a model using mean and shape of syllable log-pitch contours as basic units.

Related Experiment Videos

  • Incorporated speaker, prosodic state, tone, and syllable class as affecting factors.
  • Employed the expectation-maximization (EM) algorithm for automatic parameter estimation.

    • Main Results:

    • Achieved low root mean squared errors (RMSEs) of 0.362 ms (closed test) and 0.373 ms (open test) in pitch period reconstruction.
    • Inferred factor values aligned well with linguistic knowledge.
    • Provided a quantitative description of tone coarticulation effects.

    Conclusions:

    • The proposed model effectively separates and quantifies the effects of various factors on Mandarin pitch contours.
    • The model offers a more precise understanding of tone sandhi and coarticulation than traditional methods.
    • It can aid in identifying prosodic phrase boundaries, enhancing speech processing applications.