• 270 likes • 624 Views
The 27-instrument sessions were grouped by family and by similar sound ... matrix (3D-View) Confusion matrix (Martin) Confusion matrix (Family grouping for ...
E N D
Slide 1:Recognition of Isolated Instrument Tones by Conservatory Students Asha Srinivasan, David Sullivan,
and Ichiro Fujinaga
Peabody Conservatory of Music
Johns Hopkins University
Slide 2:Overview Background
Aims
Method
Set-up of previous experiments
Results
Conclusions
Slide 3:Background Musicians have a remarkable ability to recognize instruments by timbre
However, previous experiments using isolated tones suggest that recognition rates range between 36.5% and 90.0%.
Recently, timbre-recognition computer models have been able to match or exceed these rates.
Slide 4:Aims Verify previous experiments
Measure the effect of ensemble experience
Generate more detailed baseline data to help evaluate computer performance
Slide 5:Method Eighty-eight subjects participated in the experiment. They were undergraduate ear-training students (66), composition students (19), and faculty (3).
Personal information was collected:
gender, degree/year, major, primary instrument, # of years formal training, orchestral/band experience, compositional/conducting experience, perfect pitch, # of years ear-training
All tones were taken from the McGill University Master Samples.
Slide 6:The Tests Two tests were performed:
The first test included four sections, involving 2, 3, 9, and 27 instruments.
In the second test, short training sessions preceded each section, involving 2, 9, and 27 instruments.
Slide 7:Training sessions Ex: announce �oboe,� play 2 - 3 oboe samples; announce �sax,� play 2-3 sax samples
The 27-instrument sessions were grouped by family and by similar sound
Slide 8:List of Instruments
Slide 9:List of Instruments
Slide 10:Previous experiments and Peabody
Slide 11:Recognition rates for previous human experiments
Slide 12:Overview of Results Comparison of previous experiments and Peabody
Family groupings
Comparison of different groups of Peabody subjects
Piano, Guitar, Voice (PGV) students vs. Non-PGV students
Effect of the short-term training sessions
Slide 13:Recognition rates for previous human experiments and Peabody results
Slide 14:Previous computer experiments
Slide 15:Recognition rates for previous computer and human experiments and Peabody
Slide 16:Confusion matrix (2-instr. & 3-instr.)
Slide 17:Confusion matrix (9-instr.)
Slide 18:Confusion matrix (3D-View)
Slide 19:Confusion matrix comparison
Slide 20:Confusion matrix (27-instr.)
Slide 21:Confusion matrix (3D-View)
Slide 22:Confusion matrix (Martin)
Slide 23:Confusion matrix (Family grouping for 9-instr. & 27-instr.)
Slide 24:Confusion matrix comparison
Slide 25:Family vs. Exact Answers
Slide 26:Recognition rates for ear-training students, composition students, and faculty
Slide 27:Piano, Guitar, Voice (PGV) students vs. Non-PGV students
Slide 28:Effects of training on ear-training (47)and composition (6) subjects
Slide 29:Conclusions Compared to previous experiments, the average scores of subjects in this experiment were considerably higher.
Subjects who play orchestral instruments tended to score higher than those who do not.
The short-term training sessions had a significant effect on the subjects� performance for the 27-instrument test only.
The excellent average score of the human subjects in this experiment presents new challenges for timbre-recognition computer models.