Audio denoising method and system
In an audio denoising method and system provided in the present disclosure, a gain coefficient corresponding to each frequency unit may be generated based on a parameter related to a frequency by using a frequency of an audio signal as a unit, and gain processing is performed on each frequency unit separately by using the gain coefficient. The gain coefficient corresponding to a frequency unit including more valid audio signals may be larger, and a gain coefficient corresponding to a frequency unit including fewer valid audio signals may be smaller, so that more audio signals corresponding to frequency parts including more valid audio signals are preserved, while less audio signals corresponding to frequency parts including fewer valid audio signals are preserved. In this way, fidelity and intelligibility of an audio signal are improved while quality of the audio signal is improved and noise is reduced.
1. An audio denoising system, comprising:
at least one storage medium storing at least one set of instruction for audio denoising; and
at least one processor in communication with the at least one storage medium, wherein during operation, the at least one processor executes the set of instructions to:
obtain a to-be-processed audio signal,
obtain at least one modulation parameter related to a frequency of the to-be-processed audio signal, wherein the at least one modulation parameter at least includes a plurality of frequency units of the to-be-processed audio signal,
based on the at least one modulation parameter and a preset gain function, obtain at least one gain coefficient corresponding to the at least one modulation parameter, wherein the at least one gain coefficient is in a negative correlation with the plurality of frequency units,
perform gain processing on the to-be-processed audio signal based on the at least one gain coefficient corresponding to the at least one modulation parameter to obtain a target audio signal, and
output the target audio signal.
2. The audio denoising system according to claim 1 , wherein the at least one modulation parameter further includes:
a plurality of signal-to-noise ratios corresponding to the plurality of frequency units.
3. The audio denoising system according to claim 1 , wherein the to-be-processed audio signal includes an audio signal obtained after an original audio signal is processed by using a first audio denoising algorithm.
4. The audio denoising system according to claim 3 , wherein the original audio signal includes at least one of:
a first audio signal output by a first-type microphone, a second audio signal output by a second-type microphone, or an audio signal obtained after fusion of the first audio signal and the second audio signal.
5. The audio denoising system according to claim 1 , wherein to perform the gain processing on the to-be-processed audio signal based on the at least one gain coefficient corresponding to the at least one modulation parameter to obtain the target audio signal, the at least one processor further executes the set of instructions to:
generate, based on the at least one modulation parameter and the preset gain function, the at least one gain coefficient corresponding to the at least one modulation parameter,
wherein the preset gain function includes a correlation between the at least one gain coefficient and the at least one modulation parameter; and
perform the gain processing on the to-be-processed audio signal based on the at least one gain coefficient to obtain the target audio signal.
6. The audio denoising system according to claim 5 , wherein the preset gain function is a monotonic function;
wherein the at least one gain coefficient is in a positive correlation with the plurality of signal-to-noise ratios.
7. The audio denoising system according to claim 6 , wherein
the at least one modulation parameter is the plurality of frequency units;
the preset gain function is a first gain function including a correlation between at least one first gain coefficient and the frequency;
the at least one gain coefficient is the at least one first gain coefficient; and
to generate, based on the at least one modulation parameter and the preset gain function, the at least one gain coefficient corresponding to the at least one modulation parameter, the at least one processor further executes the set of instructions to:
generate, based on the plurality of frequency units and the first gain function, a plurality of first gain coefficients corresponding to the plurality of frequency units.
8. The audio denoising system according to claim 6 , wherein
the at least one modulation parameter is the plurality of signal-to-noise ratios corresponding to the plurality of frequency units;
the preset gain function is a second gain function including a correlation between at least one second gain coefficient and the plurality of signal-to-noise ratios;
the at least one gain coefficient is the at least one second gain coefficient; and
to generate, based on the at least one modulation parameter and the preset gain function, the at least one gain coefficient corresponding to the at least one modulation parameter, the at least one processor further executes the set of instructions to:
generate, based on the plurality of signal-to-noise ratios and the second gain function, a plurality of second gain coefficients corresponding to the plurality of frequency units.
9. The audio denoising system according to claim 6 , wherein
the at least one modulation parameter is the plurality of frequency units and the plurality of signal-to-noise ratios corresponding to the plurality of frequency units;
the preset gain function is a third gain function including a correlation between at least one third gain coefficient and the frequency and the plurality of signal-to-noise ratios; the at least one gain coefficient is the at least one third gain coefficient; and
to generate, based on the at least one modulation parameter and the preset gain function, the at least one gain coefficient corresponding to the at least one modulation parameter, the at least one processor further executes the set of instructions to:
generate, based on the plurality of signal-to-noise ratios, the plurality of frequency units, and the third gain function, a plurality of third gain coefficients corresponding to the plurality of frequency units.
10. The audio denoising system according to claim 6 , wherein the preset gain function is a function based on a sigmoid function.
11. The audio denoising system according to claim 5 , wherein to perform the gain processing on the to-be-processed audio signal based on the at least one gain coefficient to obtain the target audio signal, the at least one processor further executes the set of instructions to:
perform the gain processing on each of the plurality of frequency units based on the at least one gain coefficient, to obtain the target audio signal.
12. The audio denoising system according to claim 1 , wherein to obtain the at least one modulation parameter related to the frequency of the to-be-processed audio signal, the at least one processor further executes the set of instructions to:
obtain at least one initial modulation parameter corresponding to the frequency of the to-be-processed audio signal; and
perform smoothing processing on a value of the at least one initial modulation parameter by using the frequency as a variable to obtain the at least one modulation parameter.
13. The audio denoising system according to claim 12 , wherein to perform the smoothing processing on the value of the at least one initial modulation parameter with the frequency as the variable, the at least one processor further executes the set of instructions to:
perform feature fusion processing on an initial signal-to-noise ratio corresponding to each of the plurality of frequency units and an initial signal-to-noise ratio corresponding to at least one frequency unit near a current frequency unit, to obtain a signal-to-noise ratio corresponding to the current frequency unit.
14. An audio denoising method, comprising:
obtaining a to-be-processed audio signal;
obtaining at least one modulation parameter related to a frequency of the to-be-processed audio signal;
based on the at least one modulation parameter and a preset gain function, obtaining at least one gain coefficient corresponding to the at least one modulation parameter, wherein the at least one gain coefficient is in a negative correlation with the plurality of frequency units;
performing gain processing on the to-be-processed audio signal based on at least one gain coefficient corresponding to the at least one modulation parameter to obtain a target audio signal; and
outputting the target audio signal,
wherein the at least one modulation parameter at least includes plurality of frequency units of the to-be-processed audio signal.
15. The audio denoising method according to claim 14 , wherein the performing of the gain processing on the to-be-processed audio signal based on the at least one gain coefficient corresponding to the at least one modulation parameter to obtain the target audio signal includes:
generating, based on the at least one modulation parameter and the preset gain function, the at least one gain coefficient corresponding to the at least one modulation parameter, wherein the preset gain function includes a correlation between the at least one gain coefficient and the at least one modulation parameter; and
performing the gain processing on the to-be-processed audio signal based on the at least one gain coefficient to obtain the target audio signal.
16. The audio denoising method according to claim 14 , wherein the preset gain function is a monotonic function;
wherein the at least one gain coefficient is in a positive correlation with the plurality of signal-to-noise ratios.
17. The audio denoising method according to claim 16 , wherein
the at least one modulation parameter is the plurality of frequency units;
the preset gain function is a first gain function including a correlation between at least one first gain coefficient and the frequency;
the at least one gain coefficient is the at least one first gain coefficient; and
the generating, based on the at least one modulation parameter and the preset gain function, of the at least one gain coefficient corresponding to the at least one modulation parameter includes:
generating, based on the plurality of frequency units and the first gain function, a plurality of first gain coefficients corresponding to the plurality of frequency units.
18. The audio denoising method according to claim 16 , the at least one modulation parameter further includes a plurality of signal-to-noise ratios corresponding to the plurality of frequency units, wherein
the at least one modulation parameter is the plurality of signal-to-noise ratios corresponding to the plurality of frequency units;
the preset gain function is a second gain function including a correlation between at least one second gain coefficient and the plurality of signal-to-noise ratios;
the at least one gain coefficient is the at least one second gain coefficient; and
the generating, based on the at least one modulation parameter and the preset gain function, of the at least one gain coefficient corresponding to the at least one modulation parameter includes:
generating, based on the plurality of signal-to-noise ratios and the second gain function, a plurality of second gain coefficients corresponding to the plurality of frequency units.
19. The audio denoising method according to claim 16 , the at least one modulation parameter further includes a plurality of signal-to-noise ratios corresponding to the plurality of frequency units, wherein
the at least one modulation parameter is the plurality of frequency units and the plurality of signal-to-noise ratios corresponding to the plurality of frequency units;
the preset gain function is a third gain function including a correlation between at least one third gain coefficient and the frequency and the plurality of signal-to-noise ratios;
the at least one gain coefficient is the at least one third gain coefficient; and
the generating, based on the at least one modulation parameter and the preset gain function, of the at least one gain coefficient corresponding to the at least one modulation parameter includes:
generating, based on the plurality of signal-to-noise ratios, the plurality of frequency units, and the third gain function, a plurality of third gain coefficients corresponding to the plurality of frequency units.
20. The audio denoising method according to claim 14 , wherein the obtaining of the at least one modulation parameter related to the frequency of the to-be-processed audio signal includes: obtaining at least one initial modulation parameter corresponding to the frequency of the to-be-processed audio signal, and performing smoothing processing on a value of the at least one initial modulation parameter by using the frequency as a variable to obtain the at least one modulation parameter,
wherein the performing of the smoothing processing on the value of the at least one initial modulation parameter with the frequency as the variable includes: performing feature fusion processing on an initial signal-to-noise ratio corresponding to each of the plurality of frequency units and an initial signal-to-noise ratio corresponding to at least one frequency unit near a current frequency unit, to obtain a signal-to-noise ratio corresponding to the current frequency unit.