Media content identification and playback

1. A media playback device comprising:

a sound-sensing device configured to record audio content;

a content output device;

a memory device encoding instructions that, when executed by a processor, cause the media playback device to:

continually record ambient sound in an environment of a user of the media playback device;

discard the recording of the ambient sound when a command is not subsequently received from the user within a period of time;

receive a command from the user to identify audio content in the environment of the user;

save a most recently recorded portion of the ambient sound including the audio content;

communicate the recorded portion of audio content to a media delivery system;

receive identifying information for the audio content from the media delivery system;

receive a media item corresponding to the audio content from the media delivery system;

without receiving an additional command from the user, initiate playback of the media item through the content output device; and

receive a playlist of additional media items selected by the media delivery system, the additional media items being related to the media item corresponding to the audio content.

2. The media playback device of claim 1 , wherein the command is a voice command received by the sound-sensing device.

3. The media playback device of claim 1 , wherein the media item and additional media items are songs sharing the same artist, album, or both.

4. The media playback device of claim 1 , wherein the memory device further encodes instructions to play a verbal announcement before playback of the media item is initiated, the verbal announcement providing the identifying information for the audio content.

5. The media playback device of claim 1 , wherein the memory device further encodes instructions to present the identifying information for the audio content on a visual display of the media playback device.

6. At least one non-transitory computer-readable medium having computer-executable instructions embodied thereon that, when executed by at least one computing device, cause the at least one computing device to:

continuously record, with a sound-sensing device, ambient sound in an environment of a user of the computing device;

discard the recording of the ambient sound when a command is not subsequently received from the user within a period of time;

receive, at a sound-sensing device, a verbal command from the user to identify a song;

after the command is received from the user, save a most recently recorded portion of the ambient sound including the song;

analyze the audio content to identify an acoustic fingerprint;

compare the acoustic fingerprint of the audio content with a database of acoustic fingerprints;

identify a song matching the audio content acoustic fingerprint; and

initiate playback of the song through a content output device of the at least one computing device, without requiring additional input;

access a playlist of additional songs related to the song, the playlist being selected by a media server application, and

after the song is finished playing, playing the playlist of additional songs through the content output device.

7. The at least one non-transitory computer-readable media of claim 6 , wherein playback of the song begins at the start of the song.

8. The at least one non-transitory computer-readable media of claim 6 , wherein the song is played back upon identification to seamlessly resume where the audio content left off at the time of identification.

9. The at least one non-transitory computer-readable media of claim 6 , wherein playback of the song begins at a distinctive portion of the song.

10. The at least one non-transitory computer-readable media of claim 6 , wherein the playlist is generated from new songs selected using machine learning.

11. The at least one non-transitory computer-readable media of claim 6 , wherein the playlist is generated using songs that a user of the computing device has indicated a preference for in the past.

12. A method of identifying audio content, the method comprising:

continually recording ambient sound in an environment of a user of a media playback device;

discarding the recording of the ambient sound when a command is not subsequently received from the user within a period of time;

receiving a command from the user to identify audio content in the environment of the user;

saving a most recently recorded portion of the ambient sound including the audio content;

communicating the recorded portion of audio content to a media delivery system;

receiving identifying information for the audio content from the media delivery system;

receiving a media item corresponding to the audio content from the media delivery system;

without receiving an additional command from the user, initiating playback of the media item through a content output device of the media playback device; and

receiving a playlist of additional media items selected by the media delivery system, the additional media items being related to the media item corresponding to the audio content.

13. The method of claim 12 , wherein the playlist includes both media items that the user of the media playback device has consumed previously and new media items; and the media items are selected for the playlist based on past listening preferences and behaviors of the user operating the media playback device.

14. The method of claim 12 , wherein the playlist is dynamically updated to include additional media content as the playlist is playing.

15. The method of claim 12 , wherein the playlist is selected using a machine learning algorithm and is dynamically updated in response to user feedback.