System and method for enhancing game performance based on key acoustic event profiles
A system, method, and computer-readable medium are disclosed for improved threat sensitivity in a gaming application. As audio streams are received during a gaming scenario, a threat profile is selected that best matches the audio streams. The threat profile is a machine language cluster of noise used to adjust speaker equalization profile to emphasize threat noises. Digital signal processing (DSP) coefficients of the speaker equalization profile are adjusted as the gaming application continues.
1. A computer-implementable method for enhancing sound threat sensitivity in a gaming application comprising:
receiving audio streams when the game application is started;
selecting a threat profile that best matches the audio streams, wherein the threat profile is a machine learning (ML) cluster;
selecting an ML cluster through supervised classification and regression modeling, wherein the ML cluster is based on a game profile;
updating digital signal processing (DSP) coefficients of a speaker equalization profile based on the threat profile and incoming audio streams, wherein the speaker equalization profile is used to mask low frequency sounds, raise sound pressure level of identified sound events streams and/or spectral response of identified sound effects, add chorus/harmonics to boost 3 kHz range for human hearing for augmenting equal loudness contours, provide different equalization for rear channels and/or off-axis sounds for applying head related transfer function, apply multi-band dynamic range compression to auto level spectral areas of focus, and provide human hearing response from sound sources behind a user; and
continuously adjusting the DSP coefficients and speaker equalization profile as the gaming application continues.
2. The method of claim 1 , wherein the gaming application determines the number of audio streams and tags each audio stream with a category used for machine cluster analysis.
3. The method of claim 1 , wherein the machine learning cluster is used for supervised classification and regression modeling.
4. The method of claim 1 , further comprising performing supervised modeling to modify the ML cluster based on success or failure of a user during a gaming scenario.
5. The method of claim 1 , wherein the gaming application determines the number of channels of the audio streams and the speaker equalization profile is adjusted per the channels.
6. The method of claim 1 further comprising providing telemetry information for the other applications to apply lights, effects, and other optimization, based on received audio streams and selected ML cluster.
7. The method of claim 1 , further comprising applying stream effects, mode effects and endpoint effects to the audio streams.
8. A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations for enhancing sound threat sensitivity in a gaming application and comprising instructions executable by the processor and configured for:
receiving audio streams when the game application is started;
selecting a threat profile that best matches the audio streams, wherein the threat profile is a machine learning (ML) cluster;
selecting an ML cluster through supervised classification and regression modeling, wherein the ML cluster is based on a game profile;
updating digital signal processing (DSP) coefficients of a speaker equalization profile based on the threat profile and incoming audio streams, wherein the speaker equalization profile is used to mask low frequency sounds, raise sound pressure level of identified sound events streams and/or spectral response of identified sound effects, add chorus/harmonics to boost 3 kHz range for human hearing for augmenting equal loudness contours, provide different equalization for rear channels and/or off-axis sounds for applying head related transfer function, apply multi-band dynamic range compression to auto level spectral areas of focus, and provide human hearing response from sound sources behind a user; and
continuously adjusting the DSP coefficients and speaker equalization profile as the gaming application continues.
9. The system of claim 8 , wherein the gaming application determines the number of audio streams and tags each audio stream with a category used for machine cluster analysis.
10. The system of claim 8 , wherein the machine learning cluster is used for supervised classification and regression modeling.
11. The system of claim 8 , further comprising performing supervised modeling to modify the ML cluster based on success or failure of a user during a gaming scenario.
12. The system of claim 8 , wherein the gaming application determines the number of channels of the audio streams and the speaker equalization profile is adjusted per the channels.
13. The system of claim 8 , further comprising providing telemetry information for other applications to apply lights, effects, and other optimization, based on received audio streams and selected ML cluster.
14. The system of claim 8 , further comprising applying stream effects, mode effects and endpoint effects to the audio streams.
15. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
receiving audio streams when the game application is started;
selecting a threat profile that best matches the audio streams, wherein the threat profile is a machine learning (ML) cluster;
selecting an ML cluster through supervised classification and regression modeling, wherein the ML cluster is based on a game profile;
updating digital signal processing (DSP) coefficients of a speaker equalization profile based on the threat profile and incoming audio streams, wherein the speaker equalization profile is used to mask low frequency sounds, raise sound pressure level of identified sound events streams and/or spectral response of identified sound effects, add chorus/harmonics to boost 3 kHz range for human hearing for augmenting equal loudness contours, provide different equalization for rear channels and/or off-axis sounds for applying head related transfer function, apply multi-band dynamic range compression to auto level spectral areas of focus, and provide human hearing response from sound sources behind a user; and
continuously adjusting the DSP coefficients and speaker equalization profile as the gaming application continues.
16. The non-transitory, computer-readable storage medium of claim 15 , wherein the gaming application determines the number of audio streams and tags each audio stream with a category used for machine cluster analysis.
17. The non-transitory, computer-readable storage medium of claim 15 , wherein the machine learning cluster is used for supervised classification and regression modeling.
18. The non-transitory, computer-readable storage medium of claim 15 further comprising performing supervised modeling to modify the ML cluster based on success or failure of a user during a gaming scenario.
19. The non-transitory, computer-readable storage medium of claim 15 , wherein the gaming application determines the number of channels of the audio streams and the speaker equalization profile is adjusted per the channels.
20. The non-transitory, computer-readable storage medium of claim 15 further comprising providing telemetry information for other applications to apply lights, effects, and other optimization, based on received audio streams and selected ML cluster.