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
Maesa japonica extracts and methods of use
6-O-substituted benzoxazole and benzothiazole compounds and methods of inhibiting CSF-1R signaling
Phenethanolamine derivatives for treatment of respiratory diseases
Apparatus for tuning a musical instrument, and a related instrument
Sabatier process and apparatus for controlling exothermic reaction
Antimicrobial flush solutions
Method and device for managing subscriber connection
  Randomly Featured Patents
Spark ignited internal combustion engine and a control system therefor
Task management for changes to shared artifacts
Method for use in the manufacturing of a fluid dynamic pressure bearing
Semiconductor integrated circuit device
Optimal solar tracking system
Method for treating liquids with wave energy from an electrical arc
Apparatus and method for detecting defects in periodic pattern on object
Inkjet printing mechanism with a displaceable platen assembly
Method and system for adaptive interleaving