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

Computer speech synthesis: its status and prospects

M Liberman1

  • 1Department of Computer and Information Science, University of Pennsylvania, Philadelphia 19104, USA.

Proceedings of the National Academy of Sciences of the United States of America
|October 24, 1995
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

Predictors and impact of postoperative atrial fibrillation following thoracic surgery: a state-of-the-art review.

Anaesthesia·2023
Same author

Risk of bleeding in patients undergoing pulmonary procedures on antiplatelet or anticoagulants: A systematic review.

Respiratory medicine·2019
Same author

Turbulent diffusion of chemically reacting flows: Theory and numerical simulations.

Physical review. E·2018
Same author

Acceleration of raindrop formation due to the tangling-clustering instability in a turbulent stratified atmosphere.

Physical review. E, Statistical, nonlinear, and soft matter physics·2015
Same author

Telomeres are shorter in placentas from pregnancies with uncontrolled diabetes.

Placenta·2014
Same author

Turbulent diffusion of chemically reacting gaseous admixtures.

Physical review. E, Statistical, nonlinear, and soft matter physics·2014
Same journal

Chemotactic self-organization captures the dynamics of mammalian hair follicle patterning.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same journal

Tomographic imaging of superconducting order using particle-hole interference.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same journal

Inhibitory potential of autologous neutralizing antibodies sets quantitative limits on the rebound-competent HIV-1 reservoir.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same journal

Inferring epidemiological parameters under an infectious phylogeography model with visitor dynamics.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same journal

Analytical modeling for suction cup designs for skin-interfaced wearable devices.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same journal

Improving cell-free metabolism through direct integration of artificial respiratory chains.

Proceedings of the National Academy of Sciences of the United States of America·2026
See all related articles

Computer speech synthesis is improving but not yet natural. Optimizing large systems using formal evaluation criteria, similar to speech recognition, shows promise for achieving truly natural synthetic speech.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Linguistics

Background:

  • Computer speech synthesis technology has advanced significantly, with sophisticated linguistic models and high intelligibility.
  • Current systems show promise for mass-market applications but still lack the naturalness required for widespread adoption.

Purpose of the Study:

  • To explore research directions for achieving fully natural synthetic speech.
  • To investigate the potential of systematic optimization of large synthesis systems using formal evaluation criteria.

Main Methods:

  • Review of current research trends in computer speech synthesis.
  • Analogy drawn from the success of formal optimization in speech recognition research.

Main Results:

Related Experiment Videos

  • Computer speech synthesis has achieved high performance in intelligibility and text analysis.
  • Systematic optimization of large synthesis systems is identified as a promising research direction.

Conclusions:

  • While current speech synthesis is advanced, further improvements are needed for ubiquitous application.
  • Applying formal optimization methods, successful in speech recognition, could lead to significant advancements in naturalness for speech synthesis.