System and method for audio noise reduction
AssigneeHoneywell International Inc.
InventorsAkash Nandi, Showvik Chakraborty
Life of this patent
Estimating the term…
Abstract
A system is provided. The system comprises at least one artificial neural network configured to: receive an audio signal; for a time period, determine if at least one human voice audio spectrum is in the audio signal; for the time period, identify at least one human voice audio power spectrum; for the time period, extract each of the at least one identified human voice audio power spectrum; remove artifacts from each extracted human voice audio power spectrum to synthesize an estimation of an original human voice prior to its distortion; and transmit the synthesized estimation of an original human voice.
Claims20
A system, comprising:
- at least one artificial neural network configured to:
- receive an audio signal;
- determine that at least one human voice audio power spectrum is in the audio signal during a time period;
- upon determining that at least one human voice audio power spectrum is in the audio signal, then identify, using known human voice audio power spectra, at least one human voice audio power spectrum in the audio signal during the time period;
- extract the at least one identified human voice audio power spectrum;
- remove artifacts from each of the at least one extracted human voice audio power spectrum to synthesize an estimation of an original human voice prior to its distortion;
- and
- transmit the synthesized estimation of an original human voice.
A method, comprising:
- receiving an audio signal;
- determining that at least one human voice audio power spectrum is in the audio signal during a time period;
- upon determining that at least one human voice audio power spectrum is in the audio signal, then identifying at least one human voice audio power spectrum in the audio signal during the time period;
- extracting the at least one identified human voice audio power spectrum;
- removing artifacts from each of the at least one extracted human voice audio power spectrum to synthesize an estimation of an original human voice prior to its distortion;
- and
- transmitting the synthesized estimation of the original human voice.
A method, comprising:
- receiving an audio signal;
- determining if frequency spectrum of the audio signal includes at least one human voice audio power spectrum;
- and
- upon determining that the frequency spectrum includes at least one human voice audio power spectrum, then:
- partitioning the frequency spectrum into sub-bands;
- identifying, using known human voice audio power spectra, at least one human voice audio power spectrum in at least one sub-band that is correlated to a human voice model;
- extracting each of the at least one identified human voice audio power spectrum;
- and
- modifying each of the at least one extracted human voice audio power spectrum to match a corresponding correlated human voice model.
Dependencies are inferred from the claim text.