20240013799. ADAPTIVE NOISE ESTIMATION simplified abstract (Dolby Laboratories Licensing Corporation)

From WikiPatents
Jump to navigation Jump to search

ADAPTIVE NOISE ESTIMATION

Organization Name

Dolby Laboratories Licensing Corporation

Inventor(s)

Davide Scaini of San Francisco (ES)

Chunghsin Yeh of Barcelona (ES)

Giulio Cengarle of Barcelona (ES)

Mark David De Burgh of Mount Colah (AU)

ADAPTIVE NOISE ESTIMATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240013799 titled 'ADAPTIVE NOISE ESTIMATION

Simplified Explanation

The abstract of this patent application describes a method for processing audio input by dividing it into speech and non-speech segments. For each frame in the non-speech segments, a time-varying noise spectrum is estimated. For each frame in the speech segments, a speech spectrum is estimated. The method then identifies non-speech frequency components in the speech spectrum and compares them with corresponding frequency components in a plurality of estimated noise spectra. The estimated noise spectrum is selected based on the result of this comparison.

  • The method divides audio input into speech and non-speech segments.
  • It estimates a time-varying noise spectrum for each frame in the non-speech segments.
  • It estimates a speech spectrum for each frame in the speech segments.
  • It identifies non-speech frequency components in the speech spectrum.
  • It compares the non-speech frequency components with corresponding frequency components in a plurality of estimated noise spectra.
  • It selects the estimated noise spectrum based on the result of the comparison.

Potential applications of this technology:

  • Noise reduction in audio recordings or communication systems.
  • Speech enhancement in noisy environments.
  • Automatic speech recognition systems.
  • Audio processing for improved audio quality in various applications.

Problems solved by this technology:

  • Reducing background noise in audio signals.
  • Improving speech intelligibility in noisy environments.
  • Enhancing the performance of speech recognition systems.
  • Improving the quality of audio recordings or communication systems.

Benefits of this technology:

  • Improved audio quality by reducing background noise.
  • Enhanced speech intelligibility in noisy environments.
  • Increased accuracy and performance of speech recognition systems.
  • Better user experience in audio applications.


Original Abstract Submitted

in some embodiments, a method, comprises: dividing, using at least one processor, an audio input into speech and non-speech segments; for each frame in each non-speech segment, estimating, using the at least one processor, a time-varying noise spectrum of the non-speech segment; for each frame in each speech segment, estimating, using the at least one processor, speech spectrum of the speech segment; for each frame in each speech segment, identifying one or more non-speech frequency components in the speech spectrum; comparing the one or more non-speech frequency components with one or more corresponding frequency components in a plurality of estimated noise spectra and selecting the estimated noise spectrum from the plurality of estimated noise spectra based on a result of the comparing.

Retrieved from "http://wikipatents.org/index.php?title=20240013799._ADAPTIVE_NOISE_ESTIMATION_simplified_abstract_(Dolby_Laboratories_Licensing_Corporation)&oldid=27280"