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 new concept for Cochlear implant speech processing

M Leisenberg1, D C Dees

  • 1Hearing and Balance Centre at the Institute for Sound and Vibration Research, Southampton University, United Kingdom.

Ear and Hearing
|February 1, 1996
PubMed
Summary

A new cochlear implant neural net, simulation and stimulation (CINSTIM) strategy shows promise for improving speech perception in prelingually deaf users and in noisy environments. Early results indicate users can learn artificial speech patterns, validating the CINSTIM approach.

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

Cutinase A of Botrytis cinerea is expressed, but not essential, during penetration of gerbera and tomato.

Molecular plant-microbe interactions : MPMI·1997
Same author

An improvement in hearing sensitivity following hearing-aid fitting in a child with an apparent sensorineural hearing impairment.

The Journal of laryngology and otology·1996
Same author

First results on patient experiments with CINSTIM: the Southampton Cochlear Implant-Neural Network stimulation framework.

The Annals of otology, rhinology & laryngology. Supplement·1995
Same author

CINSTIM: the Southampton Cochlear Implant-Neural Network Simulation and Stimulation framework: implementation advances of a new, neural net-based speech-processing concept.

The Annals of otology, rhinology & laryngology. Supplement·1995
Same author

A new concept for cochlear implant speech processing for prelingually deaf children.

Advances in oto-rhino-laryngology·1995
Same author

Otoacoustic emissions and auditory brainstem responses in the newborn.

Archives of disease in childhood·1991

Area of Science:

  • Audiology
  • Biomedical Engineering
  • Artificial Intelligence

Background:

  • Cochlear implant technology aims to restore hearing for individuals with severe to profound hearing loss.
  • Current cochlear implant systems face challenges in speech perception, particularly in noisy environments and during early rehabilitation for prelingually deaf users.

Purpose of the Study:

  • To introduce and evaluate a novel speech processing concept, Cochlear Implant Neural Net, Simulation and Stimulation (CINSTIM).
  • To enhance speech perception in prelingually deaf cochlear implant users during early rehabilitation.
  • To improve speech-in-noise perception for all cochlear implant users.

Main Methods:

  • The CINSTIM strategy utilizes discrete, distinguishable stimulus patterns and robust speech processing.

Related Experiment Videos

  • An embedded Kohonen classifier, employing unsupervised neural network algorithms, is central to the processing concept.
  • The approach allows for the assessment and comparison of different speech processing methods within existing cochlear implant hardware.

    • Main Results:

    • Initial experiments validated the CINSTIM processing scheme and its software implementation.
    • A set of distinguishable stimulus patterns was developed and tested with experienced cochlear implant users.
    • Test subjects achieved up to 60% recognition of artificial patterns after brief training sessions.

    Conclusions:

    • The CINSTIM approach demonstrates feasibility and potential for improving cochlear implant speech processing.
    • The system's compatibility with various digital cochlear implant systems broadens its applicability.
    • Further evaluation is ongoing to fully realize the benefits for diverse user groups.