Back to results
US 11,146,607 B1Granted
Smart noise cancellation
AssigneeDialpad, Inc.
InventorsQian-Yu Tang, John Rector, Kathiravan Ramaswami
Life of this patent
Estimating the term…
Abstract
A system and method are described for smart noise cancellation. In some implementations, the system may receive audio data describing an audio signal, which the system may use to determine a set of frames of the audio signal. Spectral analysis, which may include a signal-to-noise ratio estimate, may be performed on the one or more frames of the audio. In some instances, the system may identify a noise frame from among the one or more frames based on the spectral analysis, and may reduce noise in the one or more frames based on the noise frame and the spectral analysis on the one or more frames of the audio signal.
Claims23
A computer-implemented method comprising:
- receiving, by a computing device, audio data describing an audio signal;
- determining, by the computing device, one or more frames of the audio signal using the audio data;
- performing, by the computing device, spectral analysis on the one or more frames of the audio signal, the spectral analysis including a signal-to-noise ratio estimate;
- identifying, by the computing device, a noise frame in the one or more frames based on the spectral analysis, the identifying including using at least one of a spectral deviation estimate and regional statistical features of the audio signal;
- and
- reducing, by the computing device, noise in the one or more frames based on the noise frame and the spectral analysis on the one or more frames of the audio signal.
3 more elements
A system comprising:
- at least one processor;
- and
- a non-transitory computer memory storing instructions that, when executed by the at least one processor, cause the system to perform a method comprising:
- receiving audio data describing an audio signal;
- determining one or more frames of the audio signal using the audio data;
- performing spectral analysis on the one or more frames of the audio signal, the spectral analysis including a signal-to-noise ratio estimate;
- identifying a noise frame in the one or more frames based on the spectral analysis, the identifying including using at least one of a spectral deviation estimate and regional statistical features of the audio signal;
- and
- reducing noise in the one or more frames based on the noise frame and the spectral analysis on the one or more frames of the audio signal.
6 more elements
A computer system, comprising:
- at least one processor;
- a computer memory;
- a Fourier Transform module receiving audio data describing an audio signal and determining a set of frames of the audio signal using the audio data;
- an audio feature detection module performing spectral analysis on the one or more frames of the audio signal, and identifying a noise frame in the one or more frames based on the spectral analysis, the spectral analysis including a signal-to-noise ratio estimate, the identifying including using at least one of a spectral deviation estimate and regional statistical features of the audio signal;
- and
- a noise cancellation module reducing noise in the one or more frames based on the noise frame and the spectral analysis on the one or more frames of the audio signal.
3 more elements
A computer-implemented method, comprising:
- receiving, by a computing device, audio data describing an audio signal;
- determining, by the computing device, one or more frames of the audio signal using the audio data;
- performing, by the computing device, a spectral analysis on the one or more frames of the audio signal, the spectral analysis including a signal-to-noise ratio estimate;
- identifying, by the computing device, a noise frame in the one or more frames based on the spectral analysis, the identifying including:
- determining a voicing factor for each of the one or more frames based on the signal-to-noise ratio estimate and whether the voicing factor satisfies at least one voicing threshold condition;
- determining if a spectral deviation satisfies a spectral deviation threshold condition;
- determining if regional statistics satisfies a regional statistics threshold condition;
- classifying a frame of the one or more frames as the noise frame based on the voicing factor satisfying the at least one voicing threshold condition, the spectral deviation satisfying the spectral deviation threshold condition, and the spectral deviation satisfying the regional statistics threshold condition;
- and
- reducing, by the computing device, noise in the one or more frames based on the noise frame and the spectral analysis on the one or more frames of the audio signal.
7 more elements
Dependencies are inferred from the claim text.