Low latency automixer integrated with voice and noise activity detection
Systems and methods are disclosed for providing voice and noise activity detection with audio automixers that can reject errant non-voice or non-human noises while maximizing signal-to-noise ratio and minimizing audio latency.
1. A method, comprising:
determining whether non-speech audio is present in an audio signal of a channel initially gated on by a mixer, wherein the mixer generates a mixed audio signal based on at least the audio signal of the channel initially gated on; and
when the non-speech audio is determined to be present in the audio signal of the channel initially gated on, overriding the mixer by gating off the channel initially gated on to cause the mixer to generate the mixed audio signal without the audio signal of the channel initially gated on.
2. The method of claim 1 , further comprising minimizing front end noise leak in the audio signal of the channel initially gated on during a time duration between (1) the mixer determining to gate on the channel initially gated on and (2) determining whether the non-speech audio is present in the audio signal of the channel initially gated on.
3. The method of claim 1 , further comprising applying a non-speech de-emphasis filter to the audio signal of the channel initially gated on.
4. The method of claim 3 , further comprising:
determining whether speech audio is present in the audio signal of the channel initially gated on; and
when the speech audio is determined to be present in the audio signal of the channel initially gated on, removing the non-speech de-emphasis filter from the audio signal of the channel initially gated on.
5. The method of claim 3 , further comprising removing the non-speech de-emphasis filter from the audio signal of the channel initially gated on after a time duration elapses that is between (1) the mixer determining to gate on the channel initially gated on and (2) determining whether the non-speech audio is present in the audio signal of the channel initially gated on.
6. The method of claim 1 , further comprising attenuating the audio signal of the channel initially gated on.
7. The method of claim 6 , further comprising:
determining whether speech audio is present in the audio signal of the channel initially gated on; and
when the speech audio is determined to be present in the audio signal of the channel initially gated on, removing the attenuation from the audio signal of the channel initially gated on.
8. The method of claim 6 , further comprising removing the attenuation from the audio signal of the channel initially gated on after a time duration elapses that is between (1) the mixer determining to gate on the channel initially gated on and (2) determining whether the non-speech audio is present in the audio signal of the channel initially gated on.
9. The method of claim 1 , further comprising applying a time varying attenuation to the audio signal of the channel initially gated on.
10. The method of claim 9 , further comprising:
determining whether speech audio is present in the audio signal of the channel initially gated on; and
when the speech audio is determined to be present in the audio signal of the channel initially gated on, removing the time varying attenuation from the audio signal of the channel initially gated on.
11. The method of claim 9 , further comprising removing the time varying attenuation from the audio signal of the channel initially gated on after a time duration elapses that is between (1) the mixer determining to gate on the channel initially gated on and (2) determining whether the non-speech audio is present in the audio signal of the channel initially gated on.
12. The method of claim 1 , further comprising applying one or more of a crest factor compressor or a crest factor limiter to the audio signal of the channel initially gated on.
13. The method of claim 12 , further comprising:
determining whether speech audio is present in the audio signal of the channel initially gated on; and
when the speech audio is determined to be present in the audio signal of the channel initially gated on, removing the one or more of the crest factor compressor or the crest factor limiter from the audio signal of the channel initially gated on.
14. The method of claim 12 , further comprising removing the one or more of the crest factor compressor or the crest factor limiter from the audio signal of the channel initially gated on after a time duration elapses that is between (1) the mixer determining to gate on the channel initially gated on and (2) determining whether the non-speech audio is present in the audio signal of the channel initially gated on.
15. The method of claim 1 , further comprising when the non-speech audio is determined to be present in the audio signal of the channel initially gated on, applying additional attenuation to the channel initially gated on after being gated off.
16. The method of claim 2 , further comprising modifying parameters related to minimizing the front end noise leak based on whether the channel initially gated on historically contains the non-speech audio or speech audio.
17. The method of claim 1 , wherein overriding the mixer comprises overriding the mixer by controlling a rate of gating off the channel initially gated on.
18. The method of claim 1 , further comprising:
determining whether speech audio is present in the audio signal of the channel initially gated on;
determining whether non-speech audio is present in a second audio signal of a second channel initially gated on by the mixer; and
when the speech audio is determined to be present in the audio signal of the channel initially gated on and when the non-speech audio is determined to be present in the second audio signal of the second channel initially gated on, applying a noise leakage filter to the audio signal of the channel initially gated on.
19. The method of claim 1 , further comprising determining to gate on the channel initially gated on by the mixer based on one or more of (1) a channel selection rule or (2) whether the audio signal of the channel initially gated on contains speech audio.
20. A system, comprising:
an activity detector configured to determine whether non-speech audio is present in an audio signal of a channel initially gated on by a mixer, wherein the mixer is configured to generate a mixed audio signal based on at least the audio signal of the channel initially gated on; and
a channel gating module in communication with the activity detector, the channel gating module configured to when the non-speech audio is determined by the activity detector to be present in the audio signal of the channel initially gated on, override the mixer to cause the mixer to:
gate off the channel initially gated on; and
generate the mixed audio signal without the audio signal of the channel initially gated on.
21. The system of claim 20 , further comprising a pre-mixer in communication with the mixer, the pre-mixer configured to minimize front end noise leak in the audio signal of the channel initially gated on during a time duration between (1) the mixer determining to gate on the channel initially gated on and (2) the activity detector determining whether the non-speech audio is present in the audio signal of the channel initially gated on.