Selecting songs with a desired tempo

1. A method for generating a media playlist of media items matching a target tempo, comprising:

receiving a seed value and a tempo signal from a client device, the tempo signal indicating a target tempo;

calculating a target tempo range associated with the target tempo;

generating a filtered playlist of media items based on the seed value and the target tempo range, wherein the media items in the filtered playlist have a tempo within the target tempo range, wherein generating the filtered playlist comprises:

identifying a media feature tempo for a media item in an initial playlist, wherein the media feature tempo is estimated by a human music analyst,

identifying a machine-learned tempo for the media item, wherein the machine-learned tempo is estimated by computer analysis,

determining whether the media feature tempo and the machine-learned tempo match,

responsive to determining that the media feature tempo and the machine-learned tempo match, determining whether the machine-learned tempo is outside the target tempo range,

discarding the media item from the initial playlist, resulting in a modified initial playlist, responsive to determining that the machine-learned tempo is outside the target tempo range to generate the filtered playlist, and

generating the filtered playlist based on the modified initial playlist; and providing the media items in the filtered playlist to the client device.

2. The method of claim 1 , wherein generating the filtered playlist further comprises:

generating the initial playlist of media items from a library of media items based on the received seed value.

3. The method of claim 2 , wherein generating the filtered playlist further comprises:

identifying a second media feature tempo for a second media item in the initial playlist, wherein the second media feature tempo is estimated by a human music analyst;

identifying a second machine-learned tempo for the second media item in the initial playlist, wherein the second machine-learned is estimated by computer analysis;

comparing the second media feature tempo and the second machine-learned tempo for the second media item to determine whether the second media feature tempo and the second machine-learned tempo match; and

responsive to determining that the second media feature tempo and the second machine-learned tempo do not match, discarding the second media item from the initial playlist.

4. The method of claim 1 , wherein determining whether the media feature tempo and the machine-learned tempo match further comprises:

determining a media feature tempo range as a margin below and above the media feature tempo;

scaling the machine-learned tempo to produce a scaled machine-learned tempo; and

determining that the media feature tempo and the machine-learned tempo match responsive to determining that the machine-learned tempo or the scaled machine-learned tempo is within the media feature tempo range.

5. The method of claim 1 , wherein calculating the target tempo range comprises:

calculating the target tempo range as a margin below and above the target tempo.

6. The method of claim 1 , wherein the received tempo signal is generated by the client device, and reflects movement of the client device or a user's periodic tapping on the client device.

7. The method of claim 1 , wherein the received tempo signal is generated by identifying characteristic time points in a series of sensor measurements made by the client device, wherein intensity of sensor measurements for the characteristic time points are above a predetermined threshold.

8. The method of claim 7 , wherein the sensor measurements are capacitive sensor measurements.

9. A non-transitory computer-readable storage medium storing executable computer program instructions for generating a media playlist of media items matching a target tempo, the computer program instructions, when executed, causing a processor to perform operations, the computer program instructions comprising instructions to:

receive a seed value and a tempo signal from a client device, the tempo signal indicating a target tempo;

calculate a target tempo range associated with the target tempo;

generate a filtered playlist of media items based on the seed value and the target tempo range, wherein the media items in the filtered playlist have a tempo within the target tempo range, wherein the instructions to generate the filtered playlist comprise instructions to:

identify a media feature tempo for a media item in an initial playlist, wherein the media feature tempo is estimated by a human music analyst,

identify a machine-learned tempo for the media item, wherein the machine-learned tempo is estimated by computer analysis,

determine whether the media feature tempo and the machine-learned tempo match,

responsive to determining that the media feature tempo and the machine-learned tempo match, determine whether the machine-learned tempo is outside the target tempo range,

discard the media item from the initial playlist, resulting in a modified initial playlist, responsive to determining that the machine-learned tempo is outside the target tempo range to generate the filtered playlist, and

generate the filtered playlist based on the modified initial playlist; and providing the media items in the filtered playlist to the client device.

10. The computer-readable storage medium of claim 9 , wherein the instructions to generate the filtered playlist further comprise instructions to:

generate the initial playlist of media items from a library of media items based on the received seed value.

11. The computer-readable storage medium of claim 10 , wherein the instructions to generate the filtered playlist further comprise instructions to:

identify a second media feature tempo for a second media item in the initial playlist, wherein the second media feature tempo is estimated by a human music analyst;

identify a second machine-learned tempo for the second media item in the initial playlist, wherein the second machine-learned is estimated by computer analysis;

compare the second media feature tempo and the second machine-learned tempo for the second media item to determine whether the second media feature tempo and the second machine-learned tempo match; and

responsive to determining that the second media feature tempo and the second machine-learned tempo do not match, discard the second media item from the initial playlist.

12. The computer-readable storage medium of claim 9 , wherein the instructions to determine whether the media feature tempo and the machine-learned tempo match further comprise instructions to:

determine a media feature tempo range as a margin below and above the media feature tempo;

scale the machine-learned tempo to produce a scaled machine-learned tempo; and

determine that the media feature tempo and the machine-learned tempo match responsive to determining that the machine-learned tempo or the scaled machine-learned tempo is within the media feature tempo range.

13. The computer-readable storage medium of claim 9 , wherein the instructions to calculate the target tempo range comprise instructions to:

calculate the target tempo range as a margin below and above the target tempo.

14. The computer-readable storage medium of claim 9 , wherein the received tempo signal is generated by the client device, and reflects movement of the client device or a user's periodic tapping on the client device.

15. A content server for generating a media playlist of media items matching a target tempo, comprising:

a processor for executing computer program instructions; and

a non-transitory computer-readable storage medium storing executable computer program instructions, the computer program instructions, when executed, causing a processor to perform operations, the computer program instructions comprising instructions to:

receive a seed value and a tempo signal from a client device, the tempo signal indicating a target tempo;

calculate a target tempo range associated with the target tempo;

generate a filtered playlist of media items based on the seed value and the target tempo range, wherein the media items in the filtered playlist have a tempo within the target tempo range, wherein the instructions to generate the filtered playlist comprise instructions to:

identify a media feature tempo for a media item in an initial playlist, wherein the media feature tempo is estimated by a human music analyst,

identify a machine-learned tempo for the media item, wherein the machine-learned tempo is estimated by computer analysis,

determine whether the media feature tempo and the machine-learned tempo match,

responsive to determining that the media feature tempo and the machine-learned tempo match, determine whether the machine-learned tempo is outside the target tempo range,

discard the media item from the initial playlist, resulting in a modified initial playlist, responsive to determining that the machine-learned tempo is outside the target tempo range to generate the filtered playlist, and

generate the filtered playlist based on the modified initial playlist; and providing the media items in the filtered playlist to the client device.

16. The content server of claim 15 , wherein the instructions to generate the filtered playlist further comprise instructions to:

generate the initial playlist of media items from a library of media items based on the received seed value.

17. The content server of claim 15 , wherein the instructions to generate the filtered playlist further comprise instructions to:

identify a second media feature tempo for a second media item in the initial playlist, wherein the second media feature tempo is estimated by a human music analyst;

identify a second machine-learned tempo for the second media item in the initial playlist, wherein the second machine-learned is estimated by computer analysis;

compare the second media feature tempo and the second machine-learned tempo for the second media item to determine whether the second media feature tempo and the second machine-learned tempo match; and

responsive to determining that the second media feature tempo and the second machine-learned tempo do not match, discard the second media item from the initial playlist.

18. The content server of claim 15 , wherein the instructions to determine whether the media feature tempo and the machine-learned tempo match further comprise instructions to:

determine a media feature tempo range as a margin below and above the media feature tempo;

scale the machine-learned tempo to produce a scaled machine-learned tempo; and

determine that the media feature tempo and the machine-learned tempo match responsive to determining that the machine-learned tempo or the scaled machine-learned tempo is within the media feature tempo range.

19. The content server of claim 15 , wherein the instructions to calculate the target tempo range comprise instructions to:

calculate the target tempo range as a margin below and above the target tempo.

20. The content server of claim 15 , wherein the received tempo signal is generated by the client device, and reflects movement of the client device or a user's periodic tapping on the client device.