Equalizer controller and controlling method
Equalizer controller and controlling method are disclosed. In one embodiment, an equalizer controller includes an audio classifier for identifying the audio type of an audio signal in real time; and an adjusting unit for adjusting an equalizer in a continuous manner based on the confidence value of the audio type as identified.
1. An equalizer controller comprising:
an audio classifier for continuously classifying an audio signal so as to identify the audio type of the audio signal; and
an adjusting unit for adjusting an equalizer in a continuous manner based on a confidence value of the audio type as identified, wherein the audio classifier is configured to classify the audio signal into multiple audio types with corresponding confidence values, and the adjusting unit is configured to consider at least some of the multiple audio types through weighting the confidence values of the multiple audio types based on the importance of the multiple audio types.
2. An equalizer controller comprising:
an audio classifier for continuously classifying an audio signal so as to identify the audio type of the audio signal; and
an adjusting unit for adjusting an equalizer in a continuous manner based on a confidence value of the audio type as identified, wherein the audio classifier is configured to classify the audio signal into multiple audio types with corresponding confidence values, and the adjusting unit is configured to consider at least some of the multiple audio types through weighting the effects of the multiple audio types based on the confidence values.
3. The equalizer controller according to claim 2 , wherein the adjusting unit is configured to consider at least one dominant audio type based on the confidence values.
4. The equalizer controller according to claim 1 , further comprising a parameter smoothing unit for, for a parameter of the equalizer adjusted by the adjusting unit, smoothing the parameter value determined by the adjusting unit at the present time based on the parameter values in the past.
5. The equalizer controller according to claim 4 , wherein the parameter smoothing unit is configured to determine a smoothed parameter value at the present by calculating a weighted sum of the parameter value determined by the adjusting unit at the present time and a smoothed parameter value of the last time.
6. The equalizer controller according to claim 5 , wherein the weights for calculating the weighted sum are adaptively changed based on the audio type of the audio signal.
7. The equalizer controller according to claim 5 , wherein the weights for calculating the weighted sum are adaptively changed based on different transition pairs from one audio type to another audio type.
8. The equalizer controller according to claim 5 , wherein the weights for calculating the weighted sum are adaptively changed based on an increasing or decreasing trend of the parameter value determined by the adjusting unit.
9. The equalizer controller according to claim 1 , wherein,
the audio classifier comprises an audio content classifier for identifying the content type of the audio signal; and
the adjusting unit is configured to positively correlate an equalization level with a confidence value of short-term music, and/or negatively correlate the equalization level with a confidence value of speech.
10. The equalizer controller according to claim 1 , wherein,
the audio classifier comprises an audio context classifier for identifying the context type of the audio signal; and
the adjusting unit is configured to positively correlate an equalization level with a confidence value of long-term music, and/or negatively correlate the equalization level with a confidence value of movie-like media and/or game.
11. The equalizer controller according to claim 1 , wherein
the audio classifier comprises an audio content classifier for identifying the content type of the audio signal; and
the adjusting unit is configured to positively correlate an equalization level with a confidence value of short-term music without dominant sources, and/or negatively correlate the equalization level with a confidence value of short-term music with dominant sources.
12. The equalizer controller according to claim 9 , wherein the adjusting unit is configured to positively correlate the equalization level with a confidence value of short-term music without dominant sources, and/or negatively correlate the equalization level with a confidence value of short-term music with dominant sources.
13. The equalizer controller according to claim 12 , wherein the adjusting unit is configured to consider the short-term music without/with dominant sources when the confidence value for the short-term music is greater than a threshold.
14. The equalizer controller according to claim 1 , wherein,
the audio classifier comprises an audio content classifier for identifying the content type of the audio signal; and
the adjusting unit is configured to positively correlate an equalization level with a confidence value of background sound, and/or negatively correlate the equalization level with a confidence value of noise.
15. The equalizer controller according to claim 1 , wherein the adjusting unit is configured to assign an equalization level and/or equalization profile and/or spectral balance preset to each audio type.
16. The equalizer controller according to claim 15 , wherein the audio classifier comprises an audio content classifier for classifying the audio signal into a short-term content type comprising at least one of short-term music, speech, background sound and noise.
17. The equalizer controller according to claim 16 , wherein the short-term music comprises at least one music cluster.
18. The equalizer controller according to claim 17 , wherein the at least one music cluster comprises a genre-based cluster, and/or an instrument-based cluster, and/or
music cluster classified based on rhythm, tempo, timbre of music and/or any other musical attributes.
19. The equalizer controller according to claim 15 , wherein the audio classifier comprises an audio context classifier for classifying the audio signal into a long-term context type comprising at least one of movie-like media, long-term music, VoIP and game.
20. An audio reproducing apparatus comprising the equalizer controller according to claim 1 .
21. An equalizer controlling method comprising:
classifying an audio signal so as to identify the audio type of the audio signal in real time; and
adjusting an equalizer in a continuous manner based on a confidence value of the audio type as identified, wherein the audio signal is classified into multiple audio types with corresponding confidence values, and the adjusting operation is configured to consider at least some of the multiple audio types through weighting the confidence values of the multiple audio types based on the importance of the multiple audio types.
22. An equalizer controlling method comprising:
classifying an audio signal so as to identify-the audio type of the audio signal in real time; and
adjusting an equalizer in a continuous manner based on a confidence value of the audio type as identified, wherein the audio signal is classified into multiple audio types with corresponding confidence values, and the adjusting operation is configured to consider at least some of the multiple audio types through weighting the effects of the multiple audio types based on the confidence values.
23. The equalizer controlling method according to claim 22 , wherein the adjusting operation is configured to consider at least one dominant audio type based on the confidence values.
24. The equalizer controlling method according to claim 21 , further comprising, for a parameter of the equalizer adjusted by the adjusting operation, smoothing the parameter value determined by the adjusting operation at the present time based on the parameter values in the past.
25. The equalizer controlling method according to claim 24 , wherein the smoothing operation is configured to determine a smoothed parameter value at the present by calculating a weighted sum of the parameter value determined by the adjusting operation at the present time and a smoothed parameter value of the last time.
26. The equalizer controlling method according to claim 25 , wherein the weights for calculating the weighted sum are adaptively changed based on the audio type of the audio signal.
27. The equalizer controlling method according to claim 25 , wherein the weights for calculating the weighted sum are adaptively changed based on different transition pairs from one audio type to another audio type.
28. The equalizer controlling method according to claim 25 , wherein the weights for calculating the weighted sum are adaptively changed based on an increasing or decreasing trend of the parameter value determined by the adjusting operation.
29. The equalizer controlling method according to claim 21 , wherein,
the operation of identifying the audio type comprises identifying the content type of the audio signal; and
the adjusting operation is configured to positively correlate an equalization level with a confidence value of short-term music, and/or negatively correlate the equalization level with a confidence value of speech.
30. The equalizer controlling method according to claim 21 , wherein,
the operation of identifying the audio type comprises identifying the context type of the audio signal; and
the adjusting operation is configured to positively correlate an equalization level with a confidence value of long-term music, and/or negatively correlate the equalization level with a confidence value of movie-like media and/or game.
31. The equalizer controlling method according to claim 21 , wherein
the operation of identifying the audio type comprises identifying the content type of the audio signal; and
the adjusting operation is configured to positively correlate an equalization level with a confidence value of short-term music without dominant sources, and/or negatively correlate the equalization level with a confidence value of short-term music with dominant sources.
32. The equalizer controlling method according to claim 29 , wherein the adjusting operation is configured to positively correlate the equalization level with a confidence value of short-term music without dominant sources, and/or negatively correlate the equalization level with a confidence value of short-term music with dominant sources.
33. The equalizer controlling method according to claim 32 , wherein the adjusting operation is configured to consider the short-term music without/with dominant sources when the confidence value for the short-term music is greater than a threshold.
34. The equalizer controlling method according to claim 21 , wherein,
the operation of identifying the audio type comprises a identifying the content type of the audio signal; and
the adjusting operation is configured to positively correlate an equalization level with a confidence value of background sound, and/or negatively correlate the equalization level with a confidence value of noise.
35. The equalizer controlling method according to claim 21 , wherein the adjusting operation is configured to assign an equalization level and/or equalization profile and/or spectral balance preset to each audio type.
36. The equalizer controlling method according to claim 35 , wherein the operation of identifying the audio type comprises classifying the audio signal into a short-term content type comprising at least one of short-term music, speech, background sound and noise.
37. The equalizer controlling method according to claim 36 , wherein the short-term music comprises at least one music cluster.
38. The equalizer controlling method according to claim 37 , wherein the at least one music cluster comprises a genre-based cluster, and/or an instrument-based cluster, and/or music cluster classified based on rhythm, tempo, timbre of music and/or any other musical attributes.
39. The equalizer controlling method according to claim 35 , wherein the operation of identifying the audio type comprises classifying the audio signal into a long-term context type comprising at least one of movie-like media, long-term music, VoIP and game.
40. A non-transitory computer-readable medium with instructions stored thereon that when executed by one or more processors perform an equalizer controlling method comprising:
classifying an audio signal so as to identify the audio type of the audio signal in real time; and
adjusting an equalizer in a continuous manner based on a confidence value of the audio type as identified, wherein the audio signal is classified into multiple audio types with corresponding confidence values, and the adjusting operation is configured to consider at least some of the multiple audio types through weighting the confidence values of the multiple audio types based on the importance of the multiple audio types.
41. A non-transitory computer-readable medium with instructions stored thereon that when executed by one or more processors perform an equalizer controlling method comprising:
classifying an audio signal so as to identify the audio type of-the audio signal in real time; and
adjusting an equalizer in a continuous manner based on a confidence value of the audio type as identified, wherein the audio signal is classified into multiple audio types with corresponding confidence values, and the adjusting operation is configured to consider at least some of the multiple audio types through weighting the effects of the multiple audio types based on the confidence values.