Your SlideShare is downloading. ×
Admire2011 slides
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×
Saving this for later? Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime – even offline.
Text the download link to your phone
Standard text messaging rates apply

Admire2011 slides

540
views

Published on

Existing semantic representations of music analysis encapsulate narrow sub-domain concepts and are frequently scoped by the context of a particular MIR task. Segmentation is a crucial abstraction in …

Existing semantic representations of music analysis encapsulate narrow sub-domain concepts and are frequently scoped by the context of a particular MIR task. Segmentation is a crucial abstraction in the investigation of phenomena which unfold over time; we present a Seg- ment Ontology as the backbone of an approach that models properties from the musicological domain independently from MIR implementations and their signal processing foundations, whilst maintain- ing an accurate and complete description of the relationships linking them. This framework provides two principal advantages which we explore through several examples: a layered separation of concerns that aligns the model with the needs of the users and systems that consume and produce the data; and the ability to link multiple analyses of differing types through transforms to and from the Segment axis.

Published in: Education, Technology

0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
540
On Slideshare
0
From Embeds
0
Number of Embeds
0
Actions
Shares
0
Downloads
5
Comments
0
Likes
0
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide

Transcript

  • 1. The Segment Ontology: Bridging Music-Generic and Domain-Specific Ben Fields Kevin Page, David De Roure Electronics and Computer Science Oxford e-Research Centre University of Southampton University of Oxford United Kingdom United Kingdom (Now at Musicmetric) Tim Crawford Department of Computing Goldsmiths, University of London United KingdomFriday, July 15, 2011
  • 2. or How to make your data useful?Friday, July 15, 2011
  • 3. or How to make your data useful? (for more than the person at the desk next door)Friday, July 15, 2011
  • 4. Overview • Introduction and background • Foundations • Ontology and approach • Worked examples • ConclusionsFriday, July 15, 2011Sorry about an ontology talk at before 10 in the morning, but we’llall do our best...
  • 5. Introduction and backgroundFriday, July 15, 2011
  • 6. AliceFriday, July 15, 2011So youve done some research. [Alice]Say on the latest and greatest in structured segmentation,
  • 7. currentFriday, July 15, 2011In some available library. (show libraries)
  • 8. currentFriday, July 15, 2011In some available library. (show libraries)
  • 9. 2,0.66152,0.56679,0.4866,0.45832,0.51859,0.70321,0.038462,0.02381,0.1,9.6469,9.8307,0.15385,0.095238,0.4,9.6469,9.83073,0.933,0.4629,0.57765,0.41229,0.96449,0.58075,0.15385,0.13333,0.18182,1.9774,1.9476,0.53846,0.46667,0.63636,1.9774,1.94764,0.97791,0.52583,0.6581,0.49102,0.99753,0.62006,0.42105,0.4,0.44444,1.2744,0.28195,0.52632,0.5,0.55556,1.2744,0.281955,0.81587,0.67237,0.62963,0.52713,0.78163,0.7697,0.41176,0.33333,0.53846,0.0855,0.0353,0.41176,0.33333,0.53846,0.0855,0.03536,0.72994,0.57989,0.60291,0.52291,0.71181,0.72818,0.28571,0.23529,0.36364,1.742,1.7181,0.42857,0.35294,0.54545,1.742,1.71817,0.80311,0.79048,0.65858,0.58822,0.74805,0.85078,0.22581,0.13725,0.63636,0.1035,5.6573,0.35484,0.21569,1,0.1035,5.65738,0.83249,0.84691,0.91465,0.91906,0.91029,0.91341,0.1,0.071429,0.16667,1.5356,1.6303,0.5,0.35714,0.83333,1.5356,1.63039,0.71925,0.72487,0.71622,0.70732,0.72535,0.87263,0.22222,0.15789,0.375,3.1349,3.7239,0.2963,0.21053,0.5,3.1349,3.723910,0.80073,0.47061,0.57382,0.4246,0.88475,0.6886,0.12903,0.11765,0.14286,2.7597,2.5612,0.51613,0.47059,0.57143,2.7597,2.561211,0.61851,0.73895,0.64422,0.74023,0.57026,0.75954,0.097561,0.064516,0.2,2.1932,3.2631,0.34146,0.22581,0.7,2.1932,3.263112,0.74449,0.52717,0.38629,0.27811,0.63223,0.68661,0.2029,0.12069,0.63636,0.028,7.3769,0.31884,0.18966,1,0.028,7.376913,0.71727,0.86226,0.76329,0.86093,0.68554,0.91858,0.17778,0.10811,0.5,0.4592,6.7539,0.26667,0.16216,0.75,0.4592,6.753914,0.58769,0.41369,0.39533,0.31693,0.52526,0.73385,0.051282,0.034483,0.1,3.7969,3.9955,0.10256,0.068966,0.2,3.7969,3.995515,0.5074,0.69885,0.48396,0.65689,0.38311,0.79331,0.086957,0.057143,0.18182,1.5785,3.1578,0.34783,0.22857,0.72727,1.5785,3.157816,0.68559,0.59077,0.42409,0.35172,0.53395,0.7233,0.081633,0.054054,0.16667,1.5063,2.2101,0.44898,0.2973,0.91667,1.5063,2.210117,0.74139,0.56784,0.46026,0.35487,0.65469,0.78644,0.11111,0.076923,0.2,4.1782,8.4177,0.22222,0.15385,0.4,4.1782,8.417718,0.67979,0.58325,0.44566,0.37536,0.54837,0.79474,0.26316,0.17857,0.5,1.1873,5.0093,0.36842,0.25,0.7,1.1873,5.009319,0.81253,0.9051,0.91347,0.9581,0.87282,0.92677,0.52632,0.41667,0.71429,0.0434,0.0449,0.52632,0.41667,0.71429,0.0434,0.044920,0.83714,0.61209,0.70376,0.57432,0.90854,0.74402,0.068966,0.0625,0.076923,2.9754,2.031,0.48276,0.4375,0.53846,2.9754,2.03121,0.89376,0.38768,0.56771,0.40344,0.95763,0.62828,0.15385,0.11765,0.22222,1.7314,1.6844,0.38462,0.29412,0.55556,1.7314,1.684422,0.73098,0.36994,0.48476,0.34891,0.79386,0.61375,0.074074,0.058824,0.1,4.5337,4.52,0.074074,0.058824,0.1,4.5337,4.5223,0.81342,0.67385,0.70745,0.62034,0.82302,0.82361,0.33962,0.2093,0.9,0.03645,5.3153,0.37736,0.23256,1,0.03645,5.315324,0.96062,0.93876,0.96236,0.93583,0.99045,0.97267,0.56,0.4375,0.77778,0.0217,0.02215,0.72,0.5625,1,0.0217,0.0221525,0.77459,0.42288,0.51335,0.39122,0.74634,0.64133,0.10526,0.068966,0.22222,1.0076,1.3836,0.47368,0.31034,1,1.0076,1.383626,0.95472,0.68849,0.7527,0.61021,0.98201,0.77237,0.5,0.375,0.75,0.0988,0.1003,0.5,0.375,0.75,0.0988,0.100327,0.83566,0.25589,0.44943,0.30091,0.88747,0.42936,0.090909,0.090909,0.090909,9.8989,9.4508,0.18182,0.18182,0.18182,9.8989,9.450828,0.97914,0.73493,0.80443,0.67377,0.99797,0.81683,0.59259,0.47059,0.8,0.0105,0.0093,0.66667,0.52941,0.9,0.0105,0.009329,0.80645,0.61323,0.62251,0.50776,0.80427,0.74071,0.34483,0.29412,0.41667,1.5031,0.8184,0.55172,0.47059,0.66667,1.5031,0.818430,0.90923,0.54316,0.55712,0.39344,0.95399,0.72868,0.34783,0.36364,0.33333,8.6931,0.02,0.43478,0.45455,0.41667,8.6931,0.0231,0.76196,0.54285,0.55984,0.44884,0.74375,0.77388,0.12903,0.10526,0.16667,5.0182,2.9525,0.32258,0.26316,0.41667,5.0182,2.952532,0.6294,0.72579,0.61369,0.6906,0.5522,0.76653,0.20408,0.125,0.55556,0.3678,7.5285,0.36735,0.225,1,0.3678,7.528533,0.71361,0.49932,0.51377,0.39335,0.74045,0.7069,0.054054,0.045455,0.066667,5.0592,4.6887,0.054054,0.045455,0.066667,5.0592,4.688734,0.87812,0.78273,0.8882,0.84875,0.9315,0.90517,0.083333,0.0625,0.125,0.8311,0.8451,0.66667,0.5,1,0.8311,0.845135,0.52626,0.59493,0.47072,0.54396,0.41486,0.6781,0.066667,0.05,0.1,5.3513,5.3533,0.26667,0.2,0.4,5.3513,5.353336,0.7758,0.668,0.75885,0.69136,0.84094,0.83209,0.055556,0.043478,0.076923,0.6617,0.6695,0.72222,0.56522,1,0.6617,0.669537,0.66605,0.84795,0.77282,0.89073,0.68247,0.86527,0.074074,0.045455,0.2,3.782,4.2649,0.14815,0.090909,0.4,3.782,4.264938,0.67684,0.67952,0.6022,0.58217,0.62365,0.72183,0.34483,0.22727,0.71429,0.0702,8.7867,0.34483,0.22727,0.71429,0.0702,8.786739,0.77119,0.29011,0.42757,0.29287,0.79174,0.52036,0.074074,0.0625,0.090909,6.9544,2.5373,0.2963,0.25,0.36364,6.9544,2.537340,0.6686,0.69894,0.66362,0.68884,0.64018,0.77925,0.29412,0.22727,0.41667,1.2845,1.286,0.41176,0.31818,0.58333,1.2845,1.28641,0.87802,0.42688,0.64649,0.48485,0.96983,0.63325,0.26087,0.27273,0.25,5.752,0.0842,0.34783,0.36364,0.33333,5.752,0.084242,0.93217,0.93379,0.97999,0.97809,0.98191,0.96683,0.08,0.0625,0.11111,0.5319,0.5334,0.64,0.5,0.88889,0.5319,0.533443,0.85864,0.57822,0.58551,0.4463,0.85095,0.7132,0.36364,0.22857,0.88889,0.0215,3.8896,0.36364,0.22857,0.88889,0.0215,3.889644,0.40868,0.54126,0.27701,0.43666,0.20285,0.75368,0.11111,0.060976,0.625,0.19375,7.5337,0.17778,0.097561,1,0.19375,7.533745,0.74572,0.64506,0.6383,0.5704,0.72454,0.80094,0.045455,0.030303,0.090909,4.0875,4.5896,0.22727,0.15152,0.45455,4.0875,4.589646,0.69984,0.61099,0.52079,0.47485,0.57657,0.72023,0.2069,0.15789,0.3,6.086,4.881,0.34483,0.26316,0.5,6.086,4.88147,0.73692,0.49052,0.40088,0.28332,0.68519,0.701,0.055556,0.045455,0.071429,8.5364,7.4664,0.22222,0.18182,0.28571,8.5364,7.466448,0.61213,0.84237,0.65889,0.91396,0.51513,0.75565,0.38462,0.26316,0.71429,0.2088,0.3753,0.46154,0.31579,0.85714,0.2088,0.375349,0.69079,0.21379,0.42485,0.3144,0.65494,0.48125,0.057143,0.041667,0.090909,5.9116,5.9343,0.11429,0.083333,0.18182,5.9116,5.934350,0.92411,0.89152,0.95957,0.93934,0.9807,0.96659,0.48276,0.35,0.77778,0.05535,0.058825,0.55172,0.4,0.88889,0.05535,0.05882551,0.83206,0.71228,0.77986,0.70502,0.87248,0.84714,0.076923,0.0625,0.1,1.0801,1.0818,0.69231,0.5625,0.9,1.0801,1.081852,0.87953,0.71423,0.69202,0.57148,0.87701,0.79044,0.38462,0.33333,0.45455,0.6287,0.0634,0.46154,0.4,0.54545,0.6287,0.063453,0.78255,0.52888,0.65775,0.52933,0.86844,0.70463,0.095238,0.071429,0.14286,0.7589,0.84535,0.47619,0.35714,0.71429,0.7589,0.8453554,0.99529,0.99446,0.99567,0.99138,1,0.99408,0.64,0.5,0.88889,0.0222,0.01945,0.64,0.5,0.88889,0.0222,0.0194555,0.78894,0.44123,0.52507,0.41323,0.7199,0.571,0.47619,0.41667,0.55556,0.05203,0.03985,0.47619,0.41667,0.55556,0.05203,0.0398556,0.83685,0.74141,0.67786,0.57816,0.81911,0.84006,0.27586,0.21053,0.4,0.7553,2.4216,0.48276,0.36842,0.7,0.7553,2.421657,0.85304,0.73158,0.81345,0.74841,0.89086,0.86108,0.32258,0.26316,0.41667,1.1351,1.4749,0.70968,0.57895,0.91667,1.1351,1.4749 Friday, July 15, 2011 So the output of the process perhaps looks like this But now someone has to use it.
  • 10. Friday, July 15, 2011 BobLike, say, this chap here. ( a musicologist) [Bob]
  • 11. 2,0.66152,0.56679,0.4866,0.45832,0.51859,0.70321,0.038462,0.02381,0.1,9.6469,9.8307,0.15385,0.095238,0.4,9.6469,9.83073,0.933,0.4629,0.57765,0.41229,0.96449,0.58075,0.15385,0.13333,0.18182,1.9774,1.9476,0.53846,0.46667,0.63636,1.9774,1.94764,0.97791,0.52583,0.6581,0.49102,0.99753,0.62006,0.42105,0.4,0.44444,1.2744,0.28195,0.52632,0.5,0.55556,1.2744,0.281955,0.81587,0.67237,0.62963,0.52713,0.78163,0.7697,0.41176,0.33333,0.53846,0.0855,0.0353,0.41176,0.33333,0.53846,0.0855,0.03536,0.72994,0.57989,0.60291,0.52291,0.71181,0.72818,0.28571,0.23529,0.36364,1.742,1.7181,0.42857,0.35294,0.54545,1.742,1.71817,0.80311,0.79048,0.65858,0.58822,0.74805,0.85078,0.22581,0.13725,0.63636,0.1035,5.6573,0.35484,0.21569,1,0.1035,5.65738,0.83249,0.84691,0.91465,0.91906,0.91029,0.91341,0.1,0.071429,0.16667,1.5356,1.6303,0.5,0.35714,0.83333,1.5356,1.63039,0.71925,0.72487,0.71622,0.70732,0.72535,0.87263,0.22222,0.15789,0.375,3.1349,3.7239,0.2963,0.21053,0.5,3.1349,3.723910,0.80073,0.47061,0.57382,0.4246,0.88475,0.6886,0.12903,0.11765,0.14286,2.7597,2.5612,0.51613,0.47059,0.57143,2.7597,2.561211,0.61851,0.73895,0.64422,0.74023,0.57026,0.75954,0.097561,0.064516,0.2,2.1932,3.2631,0.34146,0.22581,0.7,2.1932,3.263112,0.74449,0.52717,0.38629,0.27811,0.63223,0.68661,0.2029,0.12069,0.63636,0.028,7.3769,0.31884,0.18966,1,0.028,7.376913,0.71727,0.86226,0.76329,0.86093,0.68554,0.91858,0.17778,0.10811,0.5,0.4592,6.7539,0.26667,0.16216,0.75,0.4592,6.753914,0.58769,0.41369,0.39533,0.31693,0.52526,0.73385,0.051282,0.034483,0.1,3.7969,3.9955,0.10256,0.068966,0.2,3.7969,3.995515,0.5074,0.69885,0.48396,0.65689,0.38311,0.79331,0.086957,0.057143,0.18182,1.5785,3.1578,0.34783,0.22857,0.72727,1.5785,3.157816,0.68559,0.59077,0.42409,0.35172,0.53395,0.7233,0.081633,0.054054,0.16667,1.5063,2.2101,0.44898,0.2973,0.91667,1.5063,2.210117,0.74139,0.56784,0.46026,0.35487,0.65469,0.78644,0.11111,0.076923,0.2,4.1782,8.4177,0.22222,0.15385,0.4,4.1782,8.417718,0.67979,0.58325,0.44566,0.37536,0.54837,0.79474,0.26316,0.17857,0.5,1.1873,5.0093,0.36842,0.25,0.7,1.1873,5.009319,0.81253,0.9051,0.91347,0.9581,0.87282,0.92677,0.52632,0.41667,0.71429,0.0434,0.0449,0.52632,0.41667,0.71429,0.0434,0.044920,0.83714,0.61209,0.70376,0.57432,0.90854,0.74402,0.068966,0.0625,0.076923,2.9754,2.031,0.48276,0.4375,0.53846,2.9754,2.03121,0.89376,0.38768,0.56771,0.40344,0.95763,0.62828,0.15385,0.11765,0.22222,1.7314,1.6844,0.38462,0.29412,0.55556,1.7314,1.684422,0.73098,0.36994,0.48476,0.34891,0.79386,0.61375,0.074074,0.058824,0.1,4.5337,4.52,0.074074,0.058824,0.1,4.5337,4.5223,0.81342,0.67385,0.70745,0.62034,0.82302,0.82361,0.33962,0.2093,0.9,0.03645,5.3153,0.37736,0.23256,1,0.03645,5.315324,0.96062,0.93876,0.96236,0.93583,0.99045,0.97267,0.56,0.4375,0.77778,0.0217,0.02215,0.72,0.5625,1,0.0217,0.0221525,0.77459,0.42288,0.51335,0.39122,0.74634,0.64133,0.10526,0.068966,0.22222,1.0076,1.3836,0.47368,0.31034,1,1.0076,1.383626,0.95472,0.68849,0.7527,0.61021,0.98201,0.77237,0.5,0.375,0.75,0.0988,0.1003,0.5,0.375,0.75,0.0988,0.100327,0.83566,0.25589,0.44943,0.30091,0.88747,0.42936,0.090909,0.090909,0.090909,9.8989,9.4508,0.18182,0.18182,0.18182,9.8989,9.450828,0.97914,0.73493,0.80443,0.67377,0.99797,0.81683,0.59259,0.47059,0.8,0.0105,0.0093,0.66667,0.52941,0.9,0.0105,0.009329,0.80645,0.61323,0.62251,0.50776,0.80427,0.74071,0.34483,0.29412,0.41667,1.5031,0.8184,0.55172,0.47059,0.66667,1.5031,0.818430,0.90923,0.54316,0.55712,0.39344,0.95399,0.72868,0.34783,0.36364,0.33333,8.6931,0.02,0.43478,0.45455,0.41667,8.6931,0.0231,0.76196,0.54285,0.55984,0.44884,0.74375,0.77388,0.12903,0.10526,0.16667,5.0182,2.9525,0.32258,0.26316,0.41667,5.0182,2.952532,0.6294,0.72579,0.61369,0.6906,0.5522,0.76653,0.20408,0.125,0.55556,0.3678,7.5285,0.36735,0.225,1,0.3678,7.528533,0.71361,0.49932,0.51377,0.39335,0.74045,0.7069,0.054054,0.045455,0.066667,5.0592,4.6887,0.054054,0.045455,0.066667,5.0592,4.688734,0.87812,0.78273,0.8882,0.84875,0.9315,0.90517,0.083333,0.0625,0.125,0.8311,0.8451,0.66667,0.5,1,0.8311,0.845135,0.52626,0.59493,0.47072,0.54396,0.41486,0.6781,0.066667,0.05,0.1,5.3513,5.3533,0.26667,0.2,0.4,5.3513,5.353336,0.7758,0.668,0.75885,0.69136,0.84094,0.83209,0.055556,0.043478,0.076923,0.6617,0.6695,0.72222,0.56522,1,0.6617,0.669537,0.66605,0.84795,0.77282,0.89073,0.68247,0.86527,0.074074,0.045455,0.2,3.782,4.2649,0.14815,0.090909,0.4,3.782,4.264938,0.67684,0.67952,0.6022,0.58217,0.62365,0.72183,0.34483,0.22727,0.71429,0.0702,8.7867,0.34483,0.22727,0.71429,0.0702,8.786739,0.77119,0.29011,0.42757,0.29287,0.79174,0.52036,0.074074,0.0625,0.090909,6.9544,2.5373,0.2963,0.25,0.36364,6.9544,2.537340,0.6686,0.69894,0.66362,0.68884,0.64018,0.77925,0.29412,0.22727,0.41667,1.2845,1.286,0.41176,0.31818,0.58333,1.2845,1.28641,0.87802,0.42688,0.64649,0.48485,0.96983,0.63325,0.26087,0.27273,0.25,5.752,0.0842,0.34783,0.36364,0.33333,5.752,0.084242,0.93217,0.93379,0.97999,0.97809,0.98191,0.96683,0.08,0.0625,0.11111,0.5319,0.5334,0.64,0.5,0.88889,0.5319,0.533443,0.85864,0.57822,0.58551,0.4463,0.85095,0.7132,0.36364,0.22857,0.88889,0.0215,3.8896,0.36364,0.22857,0.88889,0.0215,3.889644,0.40868,0.54126,0.27701,0.43666,0.20285,0.75368,0.11111,0.060976,0.625,0.19375,7.5337,0.17778,0.097561,1,0.19375,7.533745,0.74572,0.64506,0.6383,0.5704,0.72454,0.80094,0.045455,0.030303,0.090909,4.0875,4.5896,0.22727,0.15152,0.45455,4.0875,4.589646,0.69984,0.61099,0.52079,0.47485,0.57657,0.72023,0.2069,0.15789,0.3,6.086,4.881,0.34483,0.26316,0.5,6.086,4.88147,0.73692,0.49052,0.40088,0.28332,0.68519,0.701,0.055556,0.045455,0.071429,8.5364,7.4664,0.22222,0.18182,0.28571,8.5364,7.466448,0.61213,0.84237,0.65889,0.91396,0.51513,0.75565,0.38462,0.26316,0.71429,0.2088,0.3753,0.46154,0.31579,0.85714,0.2088,0.375349,0.69079,0.21379,0.42485,0.3144,0.65494,0.48125,0.057143,0.041667,0.090909,5.9116,5.9343,0.11429,0.083333,0.18182,5.9116,5.934350,0.92411,0.89152,0.95957,0.93934,0.9807,0.96659,0.48276,0.35,0.77778,0.05535,0.058825,0.55172,0.4,0.88889,0.05535,0.05882551,0.83206,0.71228,0.77986,0.70502,0.87248,0.84714,0.076923,0.0625,0.1,1.0801,1.0818,0.69231,0.5625,0.9,1.0801,1.081852,0.87953,0.71423,0.69202,0.57148,0.87701,0.79044,0.38462,0.33333,0.45455,0.6287,0.0634,0.46154,0.4,0.54545,0.6287,0.063453,0.78255,0.52888,0.65775,0.52933,0.86844,0.70463,0.095238,0.071429,0.14286,0.7589,0.84535,0.47619,0.35714,0.71429,0.7589,0.8453554,0.99529,0.99446,0.99567,0.99138,1,0.99408,0.64,0.5,0.88889,0.0222,0.01945,0.64,0.5,0.88889,0.0222,0.0194555,0.78894,0.44123,0.52507,0.41323,0.7199,0.571,0.47619,0.41667,0.55556,0.05203,0.03985,0.47619,0.41667,0.55556,0.05203,0.0398556,0.83685,0.74141,0.67786,0.57816,0.81911,0.84006,0.27586,0.21053,0.4,0.7553,2.4216,0.48276,0.36842,0.7,0.7553,2.421657,0.85304,0.73158,0.81345,0.74841,0.89086,0.86108,0.32258,0.26316,0.41667,1.1351,1.4749,0.70968,0.57895,0.91667,1.1351,1.4749 Friday, July 15, 2011 Does he know how what to do with your data?
  • 12. <rdf:Description rdf:about="http://purl.org/ontology/mo/mf/StructuralSegment"> <rdfs:subClassOf rdf:resource="http://purl.org/NET/c4dm/event.owl#Event"/> </rdf:Description> <mf:StructuralSegment rdf:about="features.n3s1"> <rdfs:label>Intro</rdfs:label> <event:time> <time:TimeInterval> <timeline:onTimeLine rdf:resource="features.n3timeline"/> <timeline:beginsAtDuration>PT0S</timeline:beginsAtDuration> <timeline:durationXSD>PT10.43S</timeline:durationXSD> </time:TimeInterval> </event:time> </mf:StructuralSegment> <mf:StructuralSegment rdf:about="features.n3s2"> <rdfs:label>First verse</rdfs:label> <event:time> <time:TimeInterval> <timeline:onTimeLine rdf:resource="features.n3timeline"/> <timeline:beginsAtDuration>PT10.43S</timeline:beginsAtDuration> <timeline:durationXSD>PT20.2S</timeline:durationXSD> </time:TimeInterval> </event:time> </mf:StructuralSegment> <mf:StructuralSegment rdf:about="features.n3s3"> <rdfs:label>First chorus</rdfs:label> <event:time> <time:TimeInterval> <timeline:onTimeLine rdf:resource="features.n3timeline"/> <timeline:beginsAtDuration>PT31.03S</timeline:beginsAtDuration> <timeline:durationXSD>PT30.42S</timeline:durationXSD> </time:TimeInterval> </event:time> </mf:StructuralSegment> <mf:StructuralSegment rdf:about="features.n3s4"> <rdfs:label>Second verse</rdfs:label> <event:time> <time:TimeInterval> <timeline:onTimeLine rdf:resource="features.n3timeline"/> <timeline:beginsAtDuration>PT1M1S</timeline:beginsAtDuration> <timeline:durationXSD>PT20.5S</timeline:durationXSD> </time:TimeInterval> </event:time> </mf:StructuralSegment> <mf:StructuralSegment rdf:about="features.n3s5"> <rdfs:label>Second chorus</rdfs:label> <event:time> <time:TimeInterval> <timeline:onTimeLine rdf:resource="features.n3timeline"/> <timeline:beginsAtDuration>PT1M21.5S</timeline:beginsAtDuration>Friday, July 15, 2011 <timeline:durationXSD>PT30S</timeline:durationXSD>What if your data looked like this: </time:TimeInterval> </event:time> </mf:StructuralSegment> <rdf:Description rdf:about="http://purl.org/ontology/mo/mf/KeyEvent"> <rdfs:subClassOf rdf:resource="http://purl.org/NET/c4dm/event.owl#Event"/>Well, thats not actually much better, but </rdf:Description> <mf:KeyEvent rdf:about="features.n3k1"> <mf:key rdf:resource="http://purl.org/NET/c4dm/keys.owl#EMinor"/> <event:time> <time:TimeInterval> <timeline:onTimeLine rdf:resource="features.n3timeline"/> <timeline:beginsAtDuration>PT10.43S</timeline:beginsAtDuration>
  • 13. enableFriday, July 15, 2011... the extra structure helps enable ...
  • 14. toolsFriday, July 15, 2011...the complexity to be hidden in tools
  • 15. modelFriday, July 15, 2011More specifically, by modelling the relationships and linksbetween all these disparate things, we make the tools cheapand easy.
  • 16. FoundationsFriday, July 15, 2011
  • 17. Foundations 1. Domain-specific musicology 2. Domain-specific MIR tasks 3. Music-generic 4. High-level RelationshipsFriday, July 15, 2011
  • 18. Foundations 1. Domain-specific musicology: concepts, in our use case, from musicology, and the human interpretation of music and sound.Friday, July 15, 2011Domain-specific musicology concepts are elements of form, such as intro, verse, chorus,bridge; sonata, minuet and trio, fugue. These are likely to be applied to sections of thesignal, for example “this section is a bridge”.**Mythical music taxonomy**
  • 19. Foundations 2. Domain-specific MIR tasks: parts of the model that relate to an MIR task, such as the elements extracted by a feature extractor, common labels from a classifier, or distance metrics.Friday, July 15, 2011Domain-specific MIR tasks encompass artifacts of the structural segmentation task, forexample a classifier might identify (and potentially label) sections that are similar; a contributortask might identify chords. Again, these concepts are likely to be applied to sections of signal.**Audio Feature ontology or related***
  • 20. Foundations 3. Music-generic: common concepts that transcend domain-specific such as Intervals, Segments, etc.Friday, July 15, 2011Music-generic concepts are common to different tasks and applications. Here the segments wouldbe those annotated using the domain-specific concepts and the alignments and relationshipsbetween them (e.g. the segment labelled as a chorus follows the segment labelled as a verse; thatone chord follows another).
  • 21. Foundations 4. High-level Relationships: the absolute and relative relationships between music generic elements, TimeLines and SegmentLines; and the maps between them.Friday, July 15, 2011Finally high-level relationships capture mappings between the musicologicallylabelled segments and the MIR task derived segments. We expand upon thisexample in Figure 6.
  • 22. Foundations 1. Domain-specific musicology 2. Domain-specific MIR tasks 3. Music-generic 4. High-level RelationshipsFriday, July 15, 2011Our ontology will deal with 3 and 4 so 1 and 2 can interact more easily (hopefully. with tools.)
  • 23. Ontology and approachFriday, July 15, 2011
  • 24. Ontology and approach owl: equivalent SubClassOf tl:Interval Segment Class OWL-time: tl:onTimeLine onSegmentLine Interval RatioMap SubClassOf e tl:TimeLine SegmentLine to from NonLinearMap tl:domainTimeLine SubClassOf isA tl:TimeLineMap SegmentLineMap NonSequentialMapFriday, July 15, 2011
  • 25. Ontology and approach owl: equivalent SubClassOf tl:Interval Segment Class OWL-time: tl:onTimeLine onSegmentLine Interval RatioMap SubClassOf e tl:TimeLine SegmentLine to from NonLinearMap tl:domainTimeLine SubClassOf isA tl:TimeLineMap SegmentLineMap NonSequentialMapFriday, July 15, 2011a tl Interval with the addition of a “label” expressing an association (SIM) that can be “placed” upon Time-Lines (TL) and SegmentLines.
  • 26. Ontology and approach owl: equivalent SubClassOf tl:Interval Segment Class OWL-time: tl:onTimeLine onSegmentLine Interval RatioMap SubClassOf e tl:TimeLine SegmentLine to from NonLinearMap tl:domainTimeLine SubClassOf isA tl:TimeLineMap SegmentLineMap NonSequentialMapFriday, July 15, 2011SegmentLine: an AbstractTimeLine and a relative complement to thetemporal TimeLine.
  • 27. Ontology and approach owl: equivalent SubClassOf tl:Interval Segment Class OWL-time: tl:onTimeLine onSegmentLine Interval RatioMap SubClassOf e tl:TimeLine SegmentLine to from NonLinearMap tl:domainTimeLine SubClassOf isA tl:TimeLineMap SegmentLineMap NonSequentialMapFriday, July 15, 2011SegmentLineMap: a means to express a high-level relation- ship betweenSegmentLines or with TimeLines; can imply relationships between Segmentson SegmentLines and TimeLines; similarly a SegmentLineMap can be used toinfer properties between Segments.
  • 28. Ontology and approach StartAtSegment 4/4Bar isA ContainsSegment ContainsSegment Segment Beat1 isA Beat2 isA beat3 isA Beat4 isA EndAtSegment sim:element ! Segment Segment Segment Segment sim:element _:Similarity a _:Similarity a sim:Similarity sim:Similarity sim:element sim:element Beat Bar Phrase Tadem Mythical Music TS4/4 isA ! Taxonomy SegmentLineMapFriday, July 15, 2011How about somethings (a bit) less abstract: 4 beats in 1 bar of 4/4music.
  • 29. Ontology and approach StartAtSegment 4/4Bar isA ContainsSegment ContainsSegment Segment Beat1 isA Beat2 isA beat3 isA Beat4 isA EndAtSegment sim:element ! Segment Segment Segment Segment sim:element _:Similarity a _:Similarity a sim:Similarity sim:Similarity sim:element sim:element Beat Bar Phrase Tadem Mythical Music TS4/4 isA ! Taxonomy SegmentLineMapFriday, July 15, 2011Red for MIR researcher [alice]Green for Musicologist [bob]
  • 30. Worked exampleFriday, July 15, 2011
  • 31. Worked example Labelled structured segmentation • Bob’s domain knowledge • Alice’s MIR processes • Mediated through the segment ontologyFriday, July 15, 2011(you remember Alice and Bob, yes?)
  • 32. Worked example onSegmentLine SL1 isA SegmentLine R onSegmentLine segmentAfter S0 isA S1 isA S2 isA S3 isA tl:Interval Segment Segment Segment Segment M a segmentBefore mo:Signal mo:recordedAs _:Similarity a _:Similarity a _:Similarity a sim:Similarity sim:Similarity sim:Similarity D _:Similarity a _:Similarity a _:Similarity a _:Similarity a sim:Similarity sim:Similarity sim:Similarity sim:Similarity "Intro" "Verse" "Refrain" a label a label a label "Help" segmentAfter mo:MusicalWork Help Intro isA Help Verse1 Help Refrain Help Verse2 Segment isA Segment isA Segment isA Segment segmentBefore Intro Verse Refrain Bridge Mythical Music TaxonomyFriday, July 15, 2011help! I need somebody [to explain linked data]help! Not just anybody [eloquent speaker prefered]help! (etc...)[explain the graph]
  • 33. Worked example onSegmentLine SL1 isA SegmentLine R onSegmentLine segmentAfter S0 isA S1 isA S2 isA S3 isA tl:Interval Segment Segment Segment Segment M a segmentBefore mo:Signal mo:recordedAs _:Similarity a _:Similarity a _:Similarity a sim:Similarity sim:Similarity sim:Similarity D _:Similarity a _:Similarity a _:Similarity a _:Similarity a sim:Similarity sim:Similarity sim:Similarity sim:Similarity "Intro" "Verse" "Refrain" a label a label a label "Help" segmentAfter mo:MusicalWork Help Intro isA Help Verse1 Help Refrain Help Verse2 Segment isA Segment isA Segment isA Segment segmentBefore Intro Verse Refrain Bridge Mythical Music TaxonomyFriday, July 15, 2011Alice’s domain-specific contribution
  • 34. Worked example onSegmentLine SL1 isA SegmentLine R onSegmentLine segmentAfter S0 isA S1 isA S2 isA S3 isA tl:Interval Segment Segment Segment Segment M a segmentBefore mo:Signal mo:recordedAs _:Similarity a _:Similarity a _:Similarity a sim:Similarity sim:Similarity sim:Similarity D _:Similarity a _:Similarity a _:Similarity a _:Similarity a sim:Similarity sim:Similarity sim:Similarity sim:Similarity "Intro" "Verse" "Refrain" a label a label a label "Help" segmentAfter mo:MusicalWork Help Intro isA Help Verse1 Help Refrain Help Verse2 Segment isA Segment isA Segment isA Segment segmentBefore Intro Verse Refrain Bridge Mythical Music TaxonomyFriday, July 15, 2011Bob’s domain specific contribution
  • 35. Conclusions • The link between MIR researcher and musicologist user is critical, yet difficult • By moving complexing to a intermediary tools to aid this link becomes cheap • Make more tools! • And the Mythical Music Taxonomy!Friday, July 15, 2011We have presented the Segment Ontology, that uniquely enables post-hoc integration across other datasets anddomain structures through a separation of concerns between segmentation, structure, and musical domains. The nextstage of our research is to deploy the ontology across the collections of ground truth and computational analysisdiscussed in section 1, integrated as a part of a Linked Data API through which researchers can access, study, andmanipulate results. Completion of the Mythical Music Taxonomy is left as an exercise for the reader.
  • 36. The End Resources and more info: http://www.linkedmusic.org/segment/ ISMIR Tutorial: http://ismir2011.linkedmusic.org/Friday, July 15, 2011
  • 37. Questions? Resources and more info: http://www.linkedmusic.org/segment/ ISMIR Tutorial: http://ismir2011.linkedmusic.org/ These slides: http://slideshare.net/bfieldsFriday, July 15, 2011

×