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

Gender recognition from speech. Part II: Fine analysis.

D G Childers1, K Wu

  • 1Department of Electrical Engineering, University of Florida, Gainesville 32611-2024.

The Journal of the Acoustical Society of America
|October 1, 1991
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

[Study on the effects of noise on hypertension and hyperglycemia among occupational workers].

Zhonghua lao dong wei sheng zhi ye bing za zhi = Zhonghua laodong weisheng zhiyebing zazhi = Chinese journal of industrial hygiene and occupational diseases·2020
Same author

Reduced E-cadherin expression as a prognostic factor in non-muscle-invasive bladder cancer: A systematic review and meta-analysis.

Progres en urologie : journal de l'Association francaise d'urologie et de la Societe francaise d'urologie·2020
Same author

Immediate early response protein 2 promotes the migration and invasion of hepatocellular carcinoma cells via regulating the activity of Rho GTPases.

Neoplasma·2020
Same author

Measures of body fatness and height in early and mid-to-late adulthood and prostate cancer: risk and mortality in The Pooling Project of Prospective Studies of Diet and Cancer.

Annals of oncology : official journal of the European Society for Medical Oncology·2020
Same author

Role of 3D Pseudocontinuous Arterial Spin-Labeling Perfusion in the Diagnosis and Follow-Up in Patients with Herpes Simplex Encephalitis.

AJNR. American journal of neuroradiology·2019
Same author

Long noncoding RNA NEAT1 promotes the growth of gastric cancer cells by regulating miR-497-5p/PIK3R1 axis.

European review for medical and pharmacological sciences·2019

This study demonstrates that digital speech processing and pattern recognition can accurately identify gender from speech. Detailed analysis of vowel characteristics, particularly formant frequencies, achieved high gender recognition rates.

Area of Science:

  • Acoustics
  • Speech Processing
  • Pattern Recognition

Background:

  • Previous research explored gender recognition from speech using various feature vectors and distance measures.
  • A coarse analysis achieved 100% gender recognition using vowel-based feature vectors.

Purpose of the Study:

  • To conduct a detailed, fine analysis of vowel characteristics for automatic gender recognition from speech.
  • To investigate the effectiveness of digital speech processing and pattern recognition techniques.

Main Methods:

  • Employed pitch synchronous closed-phase analysis and a weighted recursive least-squares method (WRLS-VFF) to extract detailed formant features (frequencies, bandwidths, amplitudes).
  • Utilized the electroglottograph signal to identify the closed-phase portion of speech.

Related Experiment Videos

  • Performed a two-way statistical analysis of variance (ANOVA) and pattern recognition to evaluate gender features.

    • Main Results:

    • Second formant frequency (98.1%) was a more accurate gender recognizer than fundamental frequency (96.2%).
    • Female speakers' spectra exhibited a steeper slope (tilt) compared to male speakers.
    • Gender information is embedded in both fundamental frequency and vocal tract resonance; female voices showed higher within-group variations.

    Conclusions:

    • Digital speech processing, particularly fine analysis of vowel acoustics, offers effective automatic gender recognition.
    • Fundamental frequency and vocal tract resonance characteristics provide redundant gender-specific information.
    • The findings contribute to understanding acoustic correlates of speaker gender.