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
Systems and methods for reducing narrow bandwidth interference contained in broad bandwidth signals
Method for forming a film
Display device substrate, method for manufacturing the same, display device, method for forming multi-layer wiring, and multi-layer wiring substrate
Multi-touch recognition resistive touch screen for recognizing multi-touch coordinates through capacitor charging time
Single-stage PFC converter with constant voltage and constant current
Collating device, collating method, and program
  Randomly Featured Patents
System and method for detecting and correcting defective pixels in a digital image sensor
Device for gripping electronic parts
Contoured mammography phantom with skin
Thin film transistor device utilizing transistors of differing material characteristics
Bumper for an automobile
Corrugated septic tank with strengthening features
Fast dual-rail dynamic logic style
Enterprise proposal management system
System and method for recycling plastics
Prism sheet having concave pentagonal