Crowd-sourced device latency estimation for synchronization of recordings in vocal capture applications
Latency on different devices (e.g., devices of differing brand, model, vintage, etc.) can vary significantly and tens of milliseconds can affect human perception of lagging and leading components of a performance. As a result, use of a uniform latency estimate across a wide variety of devices is unlikely to provide good results, and hand-estimating round-trip latency across a wide variety of devices is costly and would constantly need to be updated for new devices. Instead, a system has been developed for crowdsourcing latency estimates.
1. A device, comprising:
at least one non-transitory memory;
one or more processors coupled to the at least one non-transitory memory and configured to read instructions from the at least one non-transitory memory to perform steps including:
receiving first audio feature analysis information associated with a first audio capture captured at a first computing device and a first corresponding audio signal,
wherein the audio feature analysis information is automatically determined by an audio feature analysis device;
estimating a round-trip latency through an audio subsystem of the first computing device based on the first audio feature analysis information; and
supplying the round-trip latency to a second computing device for use in connection with vocal performance captures by the second computing device.
2. The device of claim 1 , wherein the round-trip latency estimate includes an input latency and an output latency through the audio subsystem of the first computing device.
3. The device of claim 1 , wherein the first and second computing devices are of a consistent hardware and software configuration.
4. The device of claim 3 , wherein the consistent hardware and software configuration includes consistency of at least one of hardware model, firmware version, operating system version, and audio subpath(s) for audio playback and capture.
5. The device of claim 1 , wherein the audio feature analysis information includes computationally-determined temporal offsets between the first audio capture and the first corresponding audio signal.
6. The device of claim 1 , wherein the first corresponding audio signal is a test signal with known temporal features.
7. The device of claim 1 , wherein the first audio capture includes a vocal performance.
8. The device of claim 7 , wherein the first corresponding audio signal includes a backing track.
9. The device of claim 7 , wherein the audio feature analysis information is determined based on syllables computationally identified in the vocal performance.
10. The device of claim 1 , wherein the steps further comprise:
receiving second audio feature analysis information associated with a second audio capture captured at a third computing device and a second corresponding audio signal; and
estimating the round-trip latency based on the first and second audio feature analysis information.
11. The device of claim 10 , wherein the first and third computing devices are of a consistent hardware and software configuration.
12. A method, comprising:
receiving first audio feature analysis information associated with a first audio capture captured at a first computing device and a first corresponding audio signal,
wherein the audio feature analysis information is automatically determined by an audio feature analysis device;
estimating a round-trip latency through an audio subsystem of the first computing device based on the first audio feature analysis information; and
supplying the round-trip latency to a second computing device for use in connection with vocal performance captures by the second computing device.
13. The method of claim 12 , wherein the round-trip latency estimate includes an input latency and an output latency through the audio subsystem of the first computing device.
14. The method of claim 12 , wherein the first and second computing devices are of a consistent hardware and software configuration.
15. The method of claim 14 , wherein the consistent hardware and software configuration includes consistency of at least one of hardware model, firmware version, operating system version, and audio subpath(s) for audio playback and capture.
16. The method of claim 12 , wherein the audio feature analysis information includes computationally-determined temporal offsets between the first audio capture and the first corresponding audio signal.
17. The method of claim 12 , wherein the first audio capture includes a vocal performance, and
wherein the first corresponding audio signal includes a backing track.
18. The method of claim 17 , wherein the audio feature analysis information is determined based on syllables computationally identified in the vocal performance.
19. The method of claim 12 , wherein the steps further comprise:
receiving second audio feature analysis information associated with a second audio capture captured at a third computing device and a second corresponding audio signal; and
estimating the round-trip latency based on the first and second audio feature analysis information.
20. The method of claim 19 , wherein the first and third computing devices are of a consistent hardware and software configuration.