Geotagged environmental audio for enhanced speech recognition accuracy

A computer storage medium encoded with a computer program, the program comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

• receiving an audio signal that corresponds to an utterance recorded by a particular mobile device;
• determining a particular geographic location associated with the particular mobile device;
• selecting from a set of geotagged audio signals that correspond to environmental audio recorded by multiple mobile devices in multiple geographic locations, a subset of geotagged audio signals that are associated with the particular geographic location and that were received from two or more of the multiple mobile devices within a predetermined period of time relative to when the utterance was recorded by the mobile device;
• and
• performing noise compensation on the audio signal that corresponds to the utterance using the subset of the geotagged audio signals.

A computer-implemented method comprising:

• receiving an audio signal that corresponds to an utterance recorded by a particular mobile device;
• determining a particular geographic location associated with the particular mobile device;
• selecting from a set of geotagged audio signals that correspond to environmental audio recorded by multiple mobile devices in multiple geographic locations, a subset of geotagged audio signals that are associated with the particular geographic location and that were received from two or more of the multiple mobile devices within a predetermined period of time relative to when the utterance was recorded by the mobile device;
• and
• performing noise compensation on the audio signal that corresponds to the utterance using the subset of the geotagged audio signals.