Device-based detection of ambient media to be used by a server to selectively provide secondary content to the device

1. A method of providing content, comprising:

receiving a set of audio features extracted from audio data captured in an audio environment associated with a device, the audio environment including ambient environment data that satisfies a threshold level;

using a stored media signature data generated based on media content data from a source, recognizing, based at least on the set of audio features, a media channel and a program being played in the audio environment, wherein the recognizing occurs during a time window defined by machine learning of activity associated with an in-use timing of the source, wherein the time window defined by the machine learning of the activity comprises applying deep neural networks to clusterize behavior to avoid the recognizing when the source is not in use;

providing secondary content based at least on semantic content data associated with the recognized media channel, and program and device information; and

performing a subsequent iteration of the receiving the set of audio features and the recognizing if a number of retries has not been met, in response to a received feature set as a result of a failure of the recognizing to recognize the media channel and the program and the device information.

2. The method of claim 1 , wherein the device is configured to sense the audio environment and extract the set of audio features.

3. The method of claim 2 , wherein the device is configured to provide the extracted set of audio features to a remote media detection server configured to perform the recognizing.

4. The method of claim 1 , wherein an application installed on the device comprises executable instructions in a non-transitory computer readable medium which, when executed using a processor comprising the device, causes a microphone at the device to sense the audio environment and causes the device to extract the set of media features.

5. The method of claim 1 , wherein the stored media signature data is generated by processing a media stream associated with the media channel and program.

6. The method of claim 1 , wherein the secondary content comprises advertising content.

7. The method of claim 2 , wherein the secondary content is provided to a media player, wherein the device information includes location information from the device, wherein the media player is executed by another device in the audio environment of the device.

8. The method of claim 1 , wherein the secondary content is provided to another device in the audio environment of the device.

9. The method of claim 8 , wherein the secondary content is provided via an application installed on the device.

10. The method of claim 1 , wherein the semantic content data comprises one or more topics.

11. The method of claim 1 , wherein the semantic content data comprises one or more advertising or other classification codes; and the secondary content is selected based on device information comprising a user profile.

12. The method of claim 1 , further comprising determining that the audio environment includes different audio data associated with multiple pieces of media content.

13. The method of claim 1 , wherein the device is configured to determine whether a condition to perform media recognition is satisfied.

14. The method of claim 1 , wherein the device comprises a client device associated with a user.

15. The method of claim 1 , wherein a determination is made that the source is in an ON state prior to the recognizing the media channel and the program and the client device.