Spectrally orthogonal audio component processing

1. A system for processing an audio signal, comprising:

a circuitry configured to:

generate a mid component and a side component from a left channel and a right channel of the audio signal;

apply a Fourier transform to the mid component and the side component to convert the mid component and the side component to a frequency domain;

generate a hyper mid component including spectral energy of the side component removed from spectral energy of the mid component by subtracting a magnitude of the side component in the frequency domain from a magnitude of the mid component in the frequency domain;

filter the hyper mid component; and

generate a left output channel and a right output channel using the filtered hyper mid component.

2. The system of claim 1 , wherein the circuitry configured to filter the hyper mid component includes the circuitry being configured to at least one of gain adjust or time delay a subband of the hyper mid component.

3. The system of claim 1 , wherein the circuitry configured to filter the hyper mid component includes the circuitry being configured to apply a dynamic range processing to the hyper mid component.

4. The system of claim 1 , wherein the circuitry configured to filter the hyper mid component includes the circuitry being configured to adjust a frequency dependent amplitude or a frequency dependent delay of the hyper mid component.

5. The system of claim 1 , wherein the circuitry configured to filter the hyper mid component includes the circuitry being configured to apply a machine-learning based style transfer, conversion, or re-synthesis to the hyper mid component.

6. The system of claim 1 , wherein the circuitry is further configured to:

generate a residual mid component including spectral energy of the hyper mid component removed from the spectral energy of the mid component;

filter the residual mid component; and

generate the left and right output channels using the filtered residual mid component.

7. The system of claim 6 , wherein the circuitry configured to filter the residual mid component includes the circuitry being configured to at least one of gain adjust or time delay a subband of the residual mid component.

8. The system of claim 6 , wherein the circuitry configured to filter the residual mid component includes the circuitry being configured to apply a dynamic range processing to the residual mid component.

9. The system of claim 6 , wherein the circuitry configured to filter the residual mid component includes the circuitry being configured to adjust a frequency dependent amplitude or a frequency dependent delay of the residual mid component.

10. The system of claim 6 , wherein the circuitry configured to filter the residual mid component includes the circuitry being configured to apply a machine-learning based style transfer, conversion, or re-synthesis to the residual mid component.

11. The system of claim 6 , wherein:

the circuitry is further configured to apply a Fourier transform to the mid component to convert the mid component to a frequency domain; and

the circuitry configured to generate the residual mid component including spectral energy of the hyper mid component removed from the spectral energy of the mid component includes the circuitry being configured to subtract a magnitude of the hyper mid component in the frequency domain from a magnitude of the mid component in the frequency domain.

12. The system of claim 1 , wherein the circuitry is further configured to:

apply an inverse Fourier transform on the hyper mid component to convert the hyper mid component in a frequency domain to a time domain;

generate a delayed mid component by time delaying the mid component;

generate a residual mid component by subtracting the hyper mid component in the time domain from the delayed mid component in the time domain;

filter the residual mid component; and

generate the left and right output channels using the filtered residual mid component.

13. The system of claim 1 , wherein the circuitry is further configured to:

generate a hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component;

filter the hyper side component; and

generate the left and right output channels using the filtered hyper side component.

14. The system of claim 13 , wherein:

the circuitry is further configured to apply a Fourier transform to the mid component and the side component to convert the mid component and the side component to a frequency domain; and

the circuitry configured to generate the hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component includes the circuitry being configured to subtract a magnitude of the mid component in the frequency domain from a magnitude of the side component in the frequency domain.

15. The system of claim 13 , wherein the circuitry configured to filter the hyper side component includes the circuitry being configured to at least one of gain adjust or time delay a subband of the hyper side component.

16. The system of claim 13 , wherein the circuitry configured to filter the hyper side component includes the circuitry being configured to apply a dynamic range processing to the hyper side component.

17. The system of claim 13 , wherein the circuitry configured to filter the hyper side component includes the circuitry being configured to adjust a frequency dependent amplitude or a frequency dependent delay of the hyper side component.

18. The system of claim 13 , wherein the circuitry configured to filter the hyper side component includes the circuitry being configured to apply a machine-learning based style transfer, conversion, or re-synthesis to the hyper side component.

19. The system of claim 1 , wherein the circuitry is further configured to:

generate a hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component;

generate a residual side component including spectral energy of the hyper side component removed from the spectral energy of the side component;

filter the residual side component; and

generate the left and right output channels using the filtered residual side component.

20. The system of claim 19 , wherein the circuitry configured to filter the residual side component includes the circuitry being configured to at least one of gain adjust or time delay a subband of the residual side component.

21. The system of claim 19 , wherein the circuitry configured to filter the residual side component includes the circuitry being configured to apply a dynamic range processing to the residual side component.

22. The system of claim 19 , wherein the circuitry configured to filter the residual side component includes the circuitry being configured to adjust a frequency dependent amplitude or a frequency dependent delay of the residual side component.

23. The system of claim 19 , wherein the circuitry configured to filter the residual side component includes the circuitry being configured to apply a machine-learning based style transfer, conversion, or re-synthesis to the residual side component.

24. The system of claim 19 , wherein:

the circuitry is further configured to apply a Fourier transform to the side component to convert the side component to a frequency domain; and

the circuitry configured to generate the residual side component including the spectral energy of the hyper side component removed from the spectral energy of the side component includes the circuitry being configured to subtract a magnitude of the hyper side component in the frequency domain from a magnitude of the side component in the frequency domain.

25. The system of claim 1 , wherein the circuitry is further configured to:

generate a hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component;

apply an inverse Fourier transform on the hyper side component to convert the hyper mid component in a frequency domain to a time domain;

generate a delayed side component by time delaying the side component;

generate a residual side component by subtracting the hyper side component in the time domain from the delayed side component in the time domain;

filter the residual side component; and

generate the left and right output channels using the filtered residual side component.

26. A non-transitory computer readable medium comprising stored program code, the program code when executed by at least one processor configures the at least one processor to:

generate a mid component and a side component from a left channel and a right channel of an audio signal;

apply a Fourier transform to the mid component and the side component to convert the mid component and the side component to a frequency domain;

generate a hyper mid component including spectral energy of the side component removed from spectral energy of the mid component by subtracting a magnitude of the side component in the frequency domain from a magnitude of the mid component in the frequency domain;

filter the hyper mid component; and

generate a left output channel and a right output channel using the filtered hyper mid component.

27. The non-transitory computer readable medium of claim 26 , wherein the program code that configures the at least one processor to filter the hyper mid component further configures the at least one processor to at least one of gain adjust or time delay a subband of the hyper mid component.

28. The non-transitory computer readable medium of claim 26 , wherein the program code that configures the at least one processor to filter the hyper mid component further configures the at least one processor to apply a dynamic range processing to the hyper mid component.

29. The non-transitory computer readable medium of claim 26 , wherein the program code that configures the at least one processor to filter the hyper mid component further configures the at least one processor to adjust a frequency dependent amplitude or a frequency dependent delay of the hyper mid component.

30. The non-transitory computer readable medium of claim 26 , wherein the program code that configures the at least one processor to filter the hyper mid component further configures the at least one processor to apply a machine-learning based style transfer, conversion, or re-synthesis to the hyper mid component.

31. The non-transitory computer readable medium of claim 26 , wherein the program code further configures the at least one processor to:

generate a residual mid component including spectral energy of the hyper mid component removed from the spectral energy of the mid component;

filter the residual mid component; and

generate the left and right output channels using the filtered residual mid component.

32. The non-transitory computer readable medium of claim 31 , wherein the program code that configures the at least one processor to filter the residual mid component further configures the at least one processor to at least one of gain adjust or time delay a subband of the residual mid component.

33. The non-transitory computer readable medium of claim 31 , wherein the program code that configures the at least one processor to filter the residual mid component further configures the at least one processor to apply a dynamic range processing to the residual mid component.

34. The non-transitory computer readable medium of claim 31 , wherein the program code that configures the at least one processor to filter the residual mid component further configures the at least one processor to adjust a frequency dependent amplitude or a frequency dependent delay of the residual mid component.

35. The non-transitory computer readable medium of claim 31 , wherein the program code that configures the at least one processor to filter the residual mid component further configures the at least one processor to apply a machine-learning based style transfer, conversion, or re-synthesis to the residual mid component.

36. The non-transitory computer readable medium of claim 31 , wherein:

the program code further configures the at least one processor to apply a Fourier transform to the mid component to convert the mid component to a frequency domain;

the program code that configures the at least one processor to generate the residual mid component including spectral energy of the hyper mid component removed from the spectral energy of the mid component further configures the at least one processor to subtract a magnitude of the hyper mid component in the frequency domain from a magnitude of the mid component in the frequency domain.

37. The non-transitory computer readable medium of claim 26 , wherein the program code further configures the at least one processor to:

apply an inverse Fourier transform on the hyper mid component to convert the hyper mid component in a frequency domain to a time domain;

generate a delayed mid component by time delaying the mid component;

generate a residual mid component by subtracting the hyper mid component in the time domain from the delayed mid component in the time domain;

filter the residual mid component; and

generate the left and right output channels using the filtered residual mid component.

38. The non-transitory computer readable medium of claim 26 , wherein the program code further configures the at least one processor to:

generate a hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component;

filter the hyper side component; and

generate the left and right output channels using the filtered hyper side component.

39. The non-transitory computer readable medium of claim 38 , wherein:

the program code further configures the at least one processor to apply a Fourier transform to the mid component and the side component to convert the mid component and the side component to a frequency domain; and

the program code that configures the at least one processor to generate the hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component further configures the at least one processor to subtract a magnitude of the mid component in the frequency domain from a magnitude of the side component in the frequency domain.

40. The non-transitory computer readable medium of claim 38 , wherein the program code that configures the at least one processor to filter the hyper side component includes program code that configures the at least one processor to at least one of gain adjust or time delay a subband of the hyper side component.

41. The non-transitory computer readable medium of claim 38 , wherein the program code that configures the at least one processor to filter the hyper side component includes program code that configures the at least one processor to apply a dynamic range processing to the hyper side component.

42. The non-transitory computer readable medium of claim 38 , wherein the program code that configures the at least one processor to filter the hyper side component includes program code that configures the at least one processor to adjust a frequency dependent amplitude or a frequency dependent delay of the hyper side component.

43. The non-transitory computer readable medium of claim 38 , wherein the program code that configures the at least one processor to filter the hyper side component includes program code that configures the at least one processor to apply a machine-learning based style transfer, conversion, or re-synthesis to the hyper side component.

44. The non-transitory computer readable medium of claim 26 , wherein the program code further configures the at least one processor to:

generate a hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component;

generate a residual side component including spectral energy of the hyper side component removed from the spectral energy of the side component;

filter the residual side component; and

generate the left and right output channels using the filtered residual side component.

45. The non-transitory computer readable medium of claim 44 , wherein the program code that configures the at least one processor to filter the residual side component further configures the at least one processor to at least one of gain adjust or time delay a subband of the residual side component.

46. The non-transitory computer readable medium of claim 44 , wherein the program code that configures the at least one processor to filter the residual side component further configures the at least one processor to apply a dynamic range processing to the residual side component.

47. The non-transitory computer readable medium of claim 44 , wherein the program code that configures the at least one processor to filter the residual side component further configures the at least one processor to adjust a frequency dependent amplitude or a frequency dependent delay of the residual side component.

48. The non-transitory computer readable medium of claim 44 , wherein the program code that configures the at least one processor to filter the residual side component further configures the at least one processor to apply a machine-learning based style transfer, conversion, or re-synthesis to the residual side component.

49. The non-transitory computer readable medium of claim 44 , wherein:

the program code further configures the at least one processor to apply a Fourier transform to the side component to convert the side component to a frequency domain; and

the program code that configures the at least one processor to generate the residual side component including the spectral energy of the hyper side component removed from the spectral energy of the side component further configures the at least one processor to subtract a magnitude of the hyper side component in the frequency domain from a magnitude of the side component in the frequency domain.

50. The non-transitory computer readable medium of claim 26 , wherein the program code further configures the at least one processor to:

generate a hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component;

apply an inverse Fourier transform on the hyper side component to convert the hyper mid component in a frequency domain to a time domain;

generating a delayed side component by time delaying the side component;

generate a residual side component by subtracting the hyper side component in the time domain from the delayed side component in the time domain;

filter the residual side component; and

generate the left and right output channels using the filtered residual side component.

51. A method for processing an audio signal, comprising, by a circuitry:

generating a mid component and a side component from a left channel and a right channel of an audio signal;

applying a Fourier transform to the mid component and the side component to convert the mid component and the side component to a frequency domain;

generating a hyper mid component including spectral energy of the side component removed from spectral energy of the mid component by subtracting a magnitude of the side component in the frequency domain from a magnitude of the mid component in the frequency domain;

filtering the hyper mid component; and

generating a left output channel and a right output channel using the filtered hyper mid component.

52. The method of claim 51 , wherein filtering the hyper mid component includes at least one of gain adjusting or time delaying a subband of the hyper mid component.

53. The method of claim 51 , wherein filtering the hyper mid component includes applying a dynamic range processing to the hyper mid component.

54. The method of claim 51 , wherein filtering the hyper mid component includes adjusting a frequency dependent amplitude or a frequency dependent delay of the hyper mid component.

55. The method of claim 51 , wherein filtering the hyper mid component includes applying a machine-learning based style transfer, conversion, or re-synthesis to the hyper mid component.

56. The method of claim 51 , further comprising, by the circuitry:

generating a residual mid component including spectral energy of the hyper mid component removed from the spectral energy of the mid component;

filtering the residual mid component; and

generating the left and right output channels using the filtered residual mid component.

57. The method of claim 56 , wherein filtering the residual mid component includes at least one of gain adjusting or time delaying a subband of the residual mid component.

58. The method of claim 56 , wherein filtering the residual mid component includes applying a dynamic range processing to the residual mid component.

59. The method of claim 56 , wherein filtering the residual mid component includes adjusting a frequency dependent amplitude or a frequency dependent delay of the residual mid component.

60. The method of claim 56 , wherein filtering the residual mid component includes applying a machine-learning based style transfer, conversion, or re-synthesis to the residual mid component.

61. The method of claim 56 , wherein:

the method further includes applying a Fourier transform to the mid component to convert the mid component to a frequency domain; and

generating the residual mid component including spectral energy of the hyper mid component removed from the spectral energy of the mid component includes subtracting a magnitude of the hyper mid component in the frequency domain from a magnitude of the mid component in the frequency domain.

62. The method of claim 51 , further comprising, by the circuitry:

applying an inverse Fourier transform on the hyper mid component to convert the hyper mid component in a frequency domain to a time domain;

generating a delayed mid component by time delaying the mid component;

generating a residual mid component by subtracting the hyper mid component in the time domain from the delayed mid component in the time domain; and

filtering the residual mid component; and

generate the left and right output channels using the filtered residual mid component.

63. The method of claim 51 , further comprising, by the circuitry:

generating a hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component;

filtering the hyper side component; and

generating the left and right output channels using the filtered hyper side component.

64. The method of claim 63 , wherein:

the method further includes, by the circuitry, applying a Fourier transform to the mid component and the side component to convert the mid component and the side component to a frequency domain; and

generating the hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component includes subtracting a magnitude of the mid component in the frequency domain from a magnitude of the side component in the frequency domain.

65. The method of claim 63 , wherein filtering the hyper side component includes at least one of gain adjusting or time delaying a subband of the hyper side component.

66. The method of claim 63 , wherein filtering the hyper side component includes applying a dynamic range processing to the hyper side component.

67. The method of claim 63 , wherein filtering the hyper side component includes adjusting a frequency dependent amplitude or a frequency dependent delay of the hyper side component.

68. The method of claim 63 , wherein filtering the hyper side component includes applying a machine-learning based style transfer, conversion, or re-synthesis to the hyper side component.

69. The method of claim 51 , further comprising:

generating a hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component;

generating a residual side component including spectral energy of the hyper side component removed from the spectral energy of the side component;

filtering the residual side component; and

generating the left and right output channels using the filtered residual side component.

70. The method of claim 69 , wherein filtering the residual side component further includes at least one of gain adjusting or time delaying a subband of the residual side component.

71. The method of claim 69 , wherein filtering the residual side component further includes applying a dynamic range processing to the residual side component.

72. The method of claim 69 , wherein filtering the residual side component further includes adjusting a frequency dependent amplitude or a frequency dependent delay of the residual side component.

73. The method of claim 69 , wherein filtering the residual side component further includes applying a machine-learning based style transfer, conversion, or re-synthesis to the residual side component.

74. The method of claim 69 , wherein:

the method further includes applying a Fourier transform to the side component to convert the side component to a frequency domain; and

generating the residual side component including the spectral energy of the hyper side component removed from the spectral energy of the side component further includes subtracting a magnitude of the hyper side component in the frequency domain from a magnitude of the side component in the frequency domain.

75. The method of claim 51 , further comprising:

generating a hyper side component including the spectral energy of the mid component removed from the spectral energy of the side component;

applying an inverse Fourier transform on the hyper side component to convert the hyper mid component in a frequency domain to a time domain;

generating a delayed side component by time delaying the side component;

generate a residual side component by subtracting the hyper side component in the time domain from the delayed side component in the time domain;

filtering the residual side component; and

generating the left and right output channels using the filtered residual side component.

76. The system of claim 1 , wherein the hyper mid component isolates portions of the mid component corresponding to spectral energy present at a center of a sound stage.

77. The non-transitory computer readable medium of claim 26 , wherein the hyper mid component isolates portions of the mid component corresponding to spectral energy present at a center of a sound stage.

78. The method of claim 51 , wherein the hyper mid component isolates portions of the mid component corresponding to spectral energy present at a center of a sound stage.