Audio source localization
AssigneeRawles LLC
InventorsChristopher D. Coley, Ramy S. Sadek, Joshua Pollack, Jeffrey P. Adams
Life of this patent
Estimating the term…
Abstract
Techniques are described for determining locations of audio sources. Audio signals are captured from multiple locations. Pairs of the audio signals are analyzed to create correlograms, indicating correlation scores corresponding to different time offsets between the signals. Based on the correlograms, various locations are analyzed to determine probabilities of audio originating from those locations. The highest probabilities are found, indicating locations containing audio sources. In some situations, the audio sources may be reflective sources, and the locations of the reflective sources may be used to determine locations of objects or surfaces.
Claims29
A system for determining a probable location of a user within an environment, the system comprising:
- one or more processors;
- a plurality of microphones;
- one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
- receiving an audio signal, representative of an utterance of the user, from each of the plurality of microphones;
- generating correlogram data for different pairs of the audio signals, wherein the correlogram data for a particular pair of the audio signals comprises correlation scores of the particular pair of the audio signals over a range of audio signal timing offsets;
- generating a source probability for each of multiple potential locations of the user based at least in part on the correlation scores of the correlogram data;
- and
- determining the probable location of the user based at least in part on the generated source probabilities.
A method for determining a probable location of an audio source within an environment, comprising:
- receiving an audio signal from each of multiple sensing locations, each of the multiple sensing locations acquiring the audio signal from air within the environment;
- generating correlogram data corresponding to one or more pairs of the audio signals;
- generating a source probability for each of multiple potential audio source locations based at least in part on the generated correlogram data;
- and
- determining the probable location of the audio source within the environment based at least in part on the generated source probabilities.
A method of surface detection within an environment, comprising:
- receiving an audio signal from each of multiple sensing locations positioned within the environment, the audio signal corresponding to audio captured by each of the multiple sensing locations though air within the environment;
- generating correlogram data corresponding to one or more pairs of the audio signals;
- generating a source probability for each of multiple potential source locations based at least in part on the generated correlogram data;
- selecting a source location based at least in part on the generated probabilities;
- and
- determining a probable location of a surface within the environment based at least in part on the selected source location.
Dependencies are inferred from the claim text.