Methods and apparatus for dynamic volume adjustment via audio classification

1. An apparatus, comprising:

at least one memory;

instructions; and

at least one processor to execute the instructions to:

analyze, with a neural network, a parameter of an audio signal associated with a first volume level to determine a classification group associated with the audio signal;

determine an input volume of the audio signal;

determine a classification gain value based on the classification group;

determine an intermediate gain value as an intermediate between the input volume and the classification gain value by applying a first weight to the input volume and a second weight to the classification gain value;

apply the intermediate gain value to the audio signal, the intermediate gain value to modify the first volume level to a second volume level; and

apply a compression value to the audio signal, the compression value to modify the second volume level to a third volume level that satisfies a target volume threshold.

2. The apparatus of claim 1 , wherein the processor is to execute the instructions to determine if a source of the audio signal has changed.

3. The apparatus of claim 2 , wherein the processor is to execute the instructions to determine if the source of the audio signal has changed is based on at least one of (1) a comparison of a current compressor gain associated with the audio signal to a previous compressor gain associated with the audio signal, (2) a comparison of a RMS power associated with the audio signal to a previous RMS power associated with the audio signal, or (3) a comparison of a current audio sample value associated with the audio signal to a previous audio sample value associated with the audio signal.

4. The apparatus of claim 2 , wherein the processor is to execute the instructions to, in response to determining the source of the audio signal has changed, reset the intermediate gain value of the audio signal.

5. The apparatus of claim 1 , wherein the classification group is associated with at least one of a (1) a genre of music represented by the audio signal, (2) a time period of music represented by the audio signal, or (3) a presence of an instrument in music represented by the audio signal.

6. The apparatus of claim 1 , wherein the processor is to execute the instructions to determine a fourth volume level over a first time period does not fall within the target volume threshold, the first time period occurring after a second time period, the third volume level associated with the second time period, and adjust the compression value to fifth volume level, an adjusted compression value to modify the fourth volume level to the fifth volume level that satisfies the target volume threshold.

7. The apparatus of claim 1 , wherein the target volume threshold is within five decibels relative to full scale (dBFS) to twenty-one dBFS.

8. An apparatus, comprising:

at least one memory;

instructions; and

at least one processor to execute the instructions to:

analyze, with a neural network, a parameter of an input audio signal associated with an input volume level to determine a classification group associated with the input audio signal;

detect a change in the input audio signal;

determine an input volume of the input audio signal;

determine a classification gain based on the classification group and the input volume;

determine a target gain value as an intermediary between the input volume and the classification gain by applying a weight to the input volume and the classification gain;

apply the target gain value to the input audio signal to provide a gain-adjusted volume; and

adjust a compression value of the input audio signal to modify the gain-adjusted volume to a target volume within a target volume range.

9. The apparatus of claim 8 , wherein the processor is to execute the instructions to detect the change in the input audio signal if a source of the input audio signal has changed based on at least one of: (1) a comparison of a current compressor gain associated with the input audio signal to a previous compressor gain associated with the input audio signal; (2) a comparison of a RMS power associated with the input audio signal to a previous RMS power associated with the input audio signal; or (3) a comparison of a current audio sample value associated with the input audio signal to a previous audio sample value associated with the input audio signal.

10. The apparatus of claim 8 , wherein the classification group is associated with at least one of: (1) a genre of music represented by the input audio signal; (2) a time period of music represented by the input audio signal; or (3) a presence of an instrument in music represented by the input audio signal.

11. The apparatus of claim 8 , wherein the processor is to execute the instructions to determine the classification group based a comparison of one or more characteristics of the input audio signal with a trained machine leaning model.

12. The apparatus of claim 8 , wherein the processor is to execute the instructions to detect the input volume by at least one of: (1) determining an average input volume of the input audio signal over a period of time; (2) determining a deviation of the input volume of the input audio signal over a period of time; or (3) determining one or more instantaneous volume values.

13. The apparatus of claim 8 , wherein the processor is to execute the instructions to determine the classification gain using a single gain value representative of a classification group based on at least one of an average dynamic range or an average volume observed in a training data for the classification group.

14. A method, comprising:

analyzing, with a neural network, a parameter of an input audio signal associated with an input volume level to determine a classification group associated with the input audio signal;

detecting a change in the input audio signal;

determining an input volume of the input audio signal;

determining a classification gain based on the classification group and the input volume;

determining a target gain value as an intermediary between the input volume and the classification gain by applying a weight to the input volume and the classification gain;

applying the target gain value to the input audio signal to provide a gain-adjusted volume; and

adjusting a compression value of the input audio signal to modify the gain-adjusted volume to a target volume within a target volume range.

15. The method of claim 14 , wherein the detecting of the change in the input audio signal includes detecting a change in a source of the input audio signal based on at least one of: (1) a comparison of a current compressor gain associated with the input audio signal to a previous compressor gain associated with the input audio signal; (2) a comparison of a RMS power associated with the input audio signal to a previous RMS power associated with the input audio signal; or (3) a comparison of a current audio sample value associated with the input audio signal to a previous audio sample value associated with the input audio signal.

16. The method of claim 14 , wherein the classification group is associated with at least one of: (1) a genre of music represented by the input audio signal; (2) a time period of music represented by the input audio signal; or (3) a presence of an instrument in music represented by the input audio signal.

17. The method of claim 14 , further including comparing one or more characteristics of the input audio signal with a trained machine leaning model to determine the classification group.

18. The method of claim 14 , wherein the detecting of the input volume includes determining at least one of: (1) an average input volume of the input audio signal over a period of time; (2) a deviation of the input volume of the input audio signal over a period of time; or (3) one or more instantaneous volume values.

19. The method of claim 14 , wherein the determining of the classification gain includes using a single gain value representative of a classification group based on at least one of an average dynamic range or an average volume observed in a training data for the classification group.