Dynamically preventing audio artifacts
The disclosure is directed to a process that can predict and prevent an audio artifact from occurring. The process can monitor the systems, processes, and execution threads on a larger system/device, such as a mobile or in-vehicle device. Using a learning algorithm, such as deep neural network (DNN), the information collected can generate a prediction of whether an audio artifact is likely to occur. The process can use a second learning algorithm, which also can be a DNN, to generate recommended system adjustments that can attempt to prevent the audio glitch from occurring. The recommendations can be for various systems and components on the device, such as changing the processing system frequency, the memory frequency, and the audio buffer size. After the audio artifact has been prevented, the system adjustments can be reversed fully or in steps to return the system to its state prior to the system adjustments.
1. A method of processing computer generated audio, comprising:
determining, based on one or more environment parameters, a probability of an audio artifact occurring when outputting an audio portion, wherein the audio portion at least partially represents a computer generated audio signal and the one or more environment parameters include a processing frequency and a memory frequency of a system used for processing the audio portion; and
adjusting at least one of the processing frequency or the memory frequency to lower the probability of an audio artifact occurring when the probability is above a threshold.
2. The method of claim 1 , wherein the system is a part of a mobile device, and the computer generated audio signal is a streamed audio signal.
3. The method of claim 1 , wherein the computer generated audio signal includes one or more synthetically generated spoken phrases.
4. The method of claim 1 , wherein adjusting the memory frequency does not lower the probability of an audio artifact occurring.
5. The method of claim 1 , wherein the adjusting includes increasing the processing frequency until the processing frequency reaches a maximum processing frequency value.
6. The method of claim 1 , wherein the adjusting includes increasing the memory frequency until the memory frequency reaches a maximum memory frequency value.
7. The method of claim 1 , further comprising reversing an adjustment made during a prior audio check interval when the probability of an audio artifact occurring is not higher than the threshold.
8. The method of claim 7 , wherein the adjustment is reversed by a step value that is a fraction of the adjustment.
9. The method of claim 1 , wherein the determining and the adjusting are executed using at least one deep neural network.
10. The method of claim 1 , wherein a size of an audio buffer of the system is adjusted in response to an increase to the processing frequency.
11. A computer program product having a series of operating instructions stored on a non-transitory computer-readable medium that directs a data processing apparatus when executed thereby to perform audio artifact prevention operations on a system used for processing an audio portion, the operations comprising:
determining, based on one or more environment parameters, a probability of an audio artifact occurring when outputting the audio portion, wherein the audio portion at least partially represents a computer generated audio signal and the one or more environment parameters include a processing frequency and a memory frequency of a system used for processing the audio portion; and
when the probability is higher than a threshold, lowering the probability by adjusting at least one of the processing frequency or the memory frequency.
12. The computer program product of claim 11 , wherein the system is a part of a mobile device, and the computer generated audio signal is a streamed audio signal.
13. The computer program product of claim 11 , wherein the computer generated audio signal includes one or more synthetically generated spoken phrases.
14. The computer program product of claim 11 , wherein the adjusting includes increasing the processing frequency until the processing frequency reaches a maximum processing frequency value.
15. The computer program product of claim 11 , wherein the adjusting includes increasing the memory frequency until the memory frequency reaches a maximum memory frequency value.
16. The computer program product of claim 11 , wherein the operations further include reversing an adjustment made during a prior audio check interval when the probability of an audio artifact occurring is not higher than the threshold.
17. An audio system comprising:
one or more processing units to perform operations that include:
collecting one or more environment parameters of the audio system, wherein the one or more environment parameters include a processing frequency of the system and a memory frequency of the system;
determining a probability of an audio artifact occurring when outputting an audio portion, wherein the audio portion at least partially represents a computer generated audio signal and the determining is based on one or more environment parameters that include a processing frequency and a memory frequency of the system; and
when the probability is higher than a threshold, lowering the probability by adjusting at least one of the processing frequency or the memory frequency.
18. The audio system of claim 17 , wherein the one or more processing units use a deep neural network to determine the probability of the audio artifact occurring.
19. The audio system of claim 17 , wherein the one or more processing units use a deep neural network to adjust at least one of the processing frequency or the memory frequency when the probability of the audio artifact occurring is higher than the threshold.
20. The audio system of claim 17 , wherein the audio system is part of a mobile device, and the computer generated audio signal is a streamed audio signal.
21. The audio system of claim 17 , wherein the computer generated audio signal includes one or more synthetically generated spoken phrases.