Audio distortion removal based on a set of reference audio samples
AssigneeInfineon Technologies Americas Corp.
InventorsOleg Kapshii, Igor Kravets, Andrii Tsemko, Ashutosh Pandey
Life of this patent
Estimating the term…
Abstract
A method includes receiving, by a processing device, an audio sample of a distorted voice. The method further includes extracting a first set of characteristics from the audio sample. The method further includes selecting a second set of characteristics. The second set of characteristics is associated with one of a set of reference audio samples. The method further includes generating an undistorted audio sample. The undistorted audio sample is based on the distorted audio sample, the first set of characteristics, and the second set of characteristics.
Claims20
A method, comprising:
- receiving, by a processing device, an audio sample of a distorted voice;
- extracting a first set of audio sample characteristics, comprising a first set of vocal attributes and a first set of non-vocal attributes of the audio sample;
- selecting a reference audio sample from a first plurality of reference audio samples based on a similarity between the first set of vocal attributes and a second set of vocal attributes of the reference audio sample;
- determining a second set of non-vocal attributes of the reference audio sample;
- and
- generating an undistorted audio sample based on the audio sample, the first set of non-vocal attributes, and the second set of non-vocal attributes by utilizing the first set of non-vocal attributes and the second set of non-vocal attributes to reduce a distortion effect of the audio sample.
A system, comprising memory and a processing device coupled to the memory, wherein the processing device is configured to:
- receive an audio sample of a distorted voice;
- extract a first set of audio sample characteristics, comprising a first set of vocal attributes and a first set of non-vocal attributes of the audio sample;
- select a reference audio sample from a first plurality of reference audio samples based on a similarity between the first set of vocal attributes and a second set of vocal attributes of the reference audio sample;
- determine a second set of non-vocal attributes of the reference audio sample;
- and
- generate an undistorted audio sample based on the audio sample, the first set of non-vocal attributes, and the second set of non-vocal attributes by utilizing the first set of non-vocal attributes and the second set of non-vocal attributes to reduce a distortion effect of the audio sample.
A non-transitory machine-readable storage medium storing instruction which, when executed, cause a processing device to perform operations comprising:
- receiving an audio sample of a distorted voice;
- extracting a first set of audio sample characteristics, comprising a first set of vocal attributes and a first set of non-vocal attributes of the audio sample;
- selecting a reference audio sample from a first plurality of reference audio samples based on a similarity between the first set of vocal attributes and a second set of vocal attributes of the reference audio sample;
- determining a second set of non-vocal attributes of the reference audio sample;
- and
- generating an undistorted audio sample based on the audio sample, the first set of non-vocal attributes, and the second set of non-vocal attributes by utilizing the first set of non-vocal attributes and the second set of non-vocal attributes to reduce a distortion effect of the audio sample.
Dependencies are inferred from the claim text.