Method and system for interacting with a user in an experiential environment
View Patent ↗Methods and systems for providing lyric information for a song within an audio signal. This may be done, for example, to allow a user to sing along with a song the user hears on a radio. To provide the lyric information, an interactive service may be accessed. A sample of an audio signal that includes at least a portion of the song may be captured. The sample of the audio signal may provided to the interactive service. Lyric information may then be received for the song at a user device. The user device may also display the lyric information in synchrony with the rendering of the song within the audio signal to, for example, allow the user to sing along with the song.
1. A method for providing a user with lyric information for a song within an audio signal, the method comprising:
capturing a sample of the audio signal, the audio signal including at least a portion of the song;
providing the sample of the audio signal to an interactive service;
receiving lyric information for the song at a user device; and
displaying the lyric information on the user device in synchrony with the song within the audio signal through a derivation of a temporal position of the captured sample.
2. The method of claim 1 , wherein displaying the lyric information occurs in real-time so that the user can read the lyrics and sing along with the song.
3. The method of claim 1 , wherein the lyric information is received in synchrony to the song.
4. The method of claim 1 , further comprising receiving user interactions on the user device.
5. The method of claim 1 further comprising accessing the interactive service, wherein accessing the interactive service comprises dialing a predetermined telephone number and interacting with the interactive service via touch tones.
6. The method of claim 1 , wherein receiving the lyric information at the user device comprises receiving portions of the lyric information as the audio signal is being played and in synchrony with the song within the audio signal as the audio signal progresses.
7. The method of claim 1 , wherein receiving the lyric information at the user device comprises receiving lyric information automatically synchronized to the song within the audio signal.
8. The method of claim 1 , wherein receiving the lyric information at the user device comprises receiving lyric information corresponding to a temporal position of the sample of the audio signal.
9. The method of claim 1 , wherein providing the sample of the audio signal to the interactive service comprises:
preprocessing the sample of the audio signal for recognition by the interactive service; and
sending the preprocessed sample of the audio signal to the interactive service.
10. The method of claim 9 , wherein preprocessing the sample comprises determining a landmark of the sample of the audio signal.
11. The method of 9 wherein preprocessing the sample comprises determining a fingerprint of the sample of the audio signal.
12. A method for providing a user with lyric information for a song within an audio signal, the method comprising:
receiving the audio signal;
capturing a sample of the audio signal, the sample including at least a portion of the song;
providing the sample of the audio signal to an interactive service;
receiving lyric information for the song within the audio signal at a user device; and
the user device synchronizing the lyric information to the audio signal such that the lyric information is displayed in correspondence with the lyrics being rendered in the audio signal through a derivation of a temporal position of the captured sample.
13. The method of claim 12 , further comprising displaying the lyric information on the user device.
14. The method of claim 12 , wherein providing the sample of the audio signal to the interactive service comprises:
preprocessing the sample of the audio signal for recognition by the interactive service; and
providing the preprocessed sample of the audio signal to the interactive service.
15. The method of claim 14 , wherein preprocessing the sample comprises determining a landmark of the sample of the audio signal.
16. The method of claim 14 , wherein preprocessing the sample comprises determining a fingerprint of the sample of the audio signal.
17. The method claim 12 , wherein displaying the lyric information occurs in real-time so that the user can read the lyrics and sing along with the song.
18. A system for providing a user with lyric information for a song within an audio signal, the system comprising:
a database of sound recordings; and
a recognition engine for:
receiving a sample of an audio signal,
identifying a song corresponding to the sample from the database of sound recordings,
deriving a temporal position of the sample within the identified song,
determining lyric information for the identified song according to the temporal position and
transmitting the lyric information, the lyric information enabling a user device to display the lyric information in synchrony with the rendering of the audio signal through the derivation of the temporal position of the sample.
19. The system of claim 18 , wherein the sample comprises a preprocessed representation of a portion of the audio signal, and the database of sound recordings comprises preprocessed representations of the sound recordings.
20. The system of claim 19 , wherein each preprocessed representation comprises at least one fingerprint and landmark pair.
21. The system of claim 20 , wherein a landmark is a timepoint in the sound recording of a reproducible location.
22. The system of claim 20 , wherein a fingerprint identifies a feature in the sound recording at or near a landmark.
23. The system of claim 18 , wherein determining a temporal position of the sample within the identified song comprises using at least one pair of landmarks corresponding to matching sample and identified song fingerprints.
24. The system of claim 18 , wherein determining a temporal position of the sample within the identified song comprises finding a peak in a histogram of differences of landmarks corresponding to matching sample and identified song fingerprints.