Resources Contact Us Home
Speech detection

Image Number 18 for United States Patent #8131543.

The subject matter of this specification can be embodied in, among other things, a method that includes receiving an audio signal, determining an energy-independent component of a portion of the audio signal associated with a spectral shape of the portion, and determining an energy-dependent component of the portion associated with a gain level of the portion. The method also comprises comparing the energy-independent and energy-dependent components to a speech model, comparing the energy-independent and energy-dependent components to a noise model, and outputting an indication whether the portion of the audio signal more closely corresponds to the speech model or to the noise model based on the comparisons.

  Recently Added Patents
Load adaptive variable frequency phase-shift full-bridge DC/DC converter
Power up a LAN module when execution of special reproduction is expected by user during reproduction of an optical disc reproduction apparatus
Ram air turbine deployment actuator
System and method for managing stakeholder impact on sustainability for an organization
Full-aperture, back-illuminated, uniform-scene for remote sensing optical payload calibration
Disengageable clip and associated article
Near field electromagnetic location system and method
  Randomly Featured Patents
Coacting infant/toddler seat/car seat/stroller system
Surface barrier tailoring of semiconductor devices utilizing scanning electron microscope produced ionizing radiation
Cabinet bulletin board
Reproducing unit for recording medium
Desktop kinetic display device
Method for the production of plant seed with modified fiber content and modified seed coat
Vane pump for continuously variable transmission
Neuroprotective compounds and pharmaceutical compositions comprising them
Thread rendezvous for read-only code in an object-oriented computing environment
Condenser microphone