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

The potential role of speech production models in automatic speech recognition

R C Rose1, J Schroeter, M M Sondhi

  • 1AT&T Bell Laboratories, Murray Hill, New Jersey 07974-0636, USA.

The Journal of the Acoustical Society of America
|March 1, 1996
PubMed
Summary

This study explores integrating speech production models into automatic speech recognition (ASR). It focuses on articulatory representations for ASR, separate from speech perception, to improve existing systems.

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

[Erratum to: Good practice procedures for acquisition and preparation of cryopreserved human amniotic membranes from donor placentas].

Der Ophthalmologe : Zeitschrift der Deutschen Ophthalmologischen Gesellschaft·2018
Same author

[Good practice procedures for acquisition and preparation of cryopreserved human amniotic membranes from donor placentas].

Der Ophthalmologe : Zeitschrift der Deutschen Ophthalmologischen Gesellschaft·2017
Same author

[In Process Citation].

Der Ophthalmologe : Zeitschrift der Deutschen Ophthalmologischen Gesellschaft·2015
Same author

[Atypical genesis of anterior ischemic optic neuropathy].

Der Ophthalmologe : Zeitschrift der Deutschen Ophthalmologischen Gesellschaft·2015
Same author

[Microkeratome and excimer laser-assisted endothelial keratoplasty (MELEK)].

Klinische Monatsblatter fur Augenheilkunde·2014
Same author

A Model to Investigate the Urinary Bladder´s Thermal Behaviour during Transurethral Resection of Prostate Tissue.

Biomedizinische Technik. Biomedical engineering·2013

Area of Science:

  • Computational Linguistics
  • Speech Processing
  • Artificial Intelligence

Background:

  • Automatic speech recognition (ASR) systems traditionally do not leverage detailed speech production information.
  • Understanding the physical process of speech production offers potential for ASR enhancement.

Purpose of the Study:

  • To investigate the challenges and applicability of using speech production models within ASR frameworks.
  • To explore the integration of articulatory representations into current ASR systems.

Main Methods:

  • Focus on articulatory representations relevant to ASR, distinct from speech perception.
  • Integration of speech production models into established ASR formalisms.

Main Results:

Related Experiment Videos

  • Identified issues associated with applying speech production models to ASR.
  • Demonstrated methods for integrating articulatory features into existing ASR architectures.

    • Conclusions:

    • Speech production models offer a viable, though challenging, avenue for improving ASR.
    • Further research into integrating articulatory information can enhance ASR performance.