Pitch Spelling Algorithms
-
Upload
lucretia-armando -
Category
Documents
-
view
18 -
download
2
description
Transcript of Pitch Spelling Algorithms
![Page 1: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/1.jpg)
Pitch Spelling Algorithms
Author: David MeredithPresented by Jie Liu
![Page 2: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/2.jpg)
About the author
Center for Computational Creativity, Department of Computing at City University, London
His research project focus on the development of algorithms for musical pattern recognition and extraction.
![Page 3: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/3.jpg)
Concept of Pitch Spelling Algorithm
Pitch spelling algorithm attempts to compute the correct pitch names of the notes in a passage of tonal music
Onset-time, MIDI note number and duration(optional)
![Page 4: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/4.jpg)
Practical Applications:
Required for MIDI-to-notation transcriptionRequired for audio-to-notation transcriptionUseful in music information retrieval and musical pattern discovery
![Page 5: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/5.jpg)
Example
![Page 6: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/6.jpg)
Example 1
Different chromatic intervals. Three occurrences of the same motive.The three patterns have the same scale-step interval structures (-1,+1,+1)Important for MIR
![Page 7: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/7.jpg)
Example 2
(a). G#4 leading note in A minor
(b) Ab4 subdominant in C minor
![Page 8: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/8.jpg)
Pitch Spelling in common practice Western tonal music
Determined by the roles of notes in the harmonic, motivic and voice-leading structures of the passage.Pitch spelling is not arbitrary.The resulting score should represent the way that the music is perceived and interpreted.
![Page 9: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/9.jpg)
Modelling the process of pitch spelling
What are the cognitive process involved when a musically trained individual do the pitch spellingUsing an algorithm to model itEvaluated by authoritative published editions of scores
![Page 10: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/10.jpg)
Three previous pitch spelling methods
Cambouropoulos (2002)Longuet-Higgins (1993)Temperley (2001)
Test Corpora: Bach’s music baroque and classical music
![Page 11: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/11.jpg)
Longuet-Higgins’s algorithm
Input: (p (keyboard position),ton,toff)Compute q (sharpness) for every note
q is the position of the pitch name of the note on the line of fifthsDesigned to be used only on monophonic melodies
Db Ab Eb Bb F C G D A E B F# C# G#
-5 –4 –3 –2 –1 0 1 2 3 4 5 6 7 8
![Page 12: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/12.jpg)
Longuet-Higgins’s algorithm
Assume every note is no more than 6 steps from tonic on the line of fifthsAssume first note is tonic or dominant of opening keyAssume consecutive notes always less than 12 steps apart on line of fifths.more than 6 steps is the evidence of a change of key
![Page 13: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/13.jpg)
Cambouropoulos’s algorithm
No priori knowledge, such as key signature, time signature, tonal centers and so on
![Page 14: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/14.jpg)
Temperley’s algorithm
Pitch Variance Rule (L-H algorithm) Assume consecutive notes
always less than 12 steps apart on line of fifths
Voice Leading RuleHarmonic Feedback Rule (in good harmonic representations)
![Page 15: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/15.jpg)
Temperley’s algorithm
Requires duration of each note and tempo---- it needs more information than other algorithms
Cannot deal with cases where two or more notes with the same pitch start at the same time
![Page 16: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/16.jpg)
Ps 13 algorithm (improved on Temperley’s)
CNT (p,n)---Kpre, KpostLetter name L(p,n)Set of tonic pitch classes X(n,l)N(l,n)=sum CNT(p,n) (p is from X(n,l))n=max N(l,n)
![Page 17: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/17.jpg)
Experimental Results (Bach’s music)Algorithm %notes
correctNumber of errors
Cambouropoulos
93.74 2599
Longuet-Higgins
99.36 265
Temperley 99.71 122
Ps 13Kpre=33,Kpost(23,25)
99.81 81
![Page 18: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/18.jpg)
Discussion on Kpre and Kpost
Best: Kpre=33, 23<=Kpost<=25Worst: Kpre = Kpost =1
Mean number of errors 109.082 and mean accuracy 99.74% (1<=Kpre, Kpost<=50)
![Page 19: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/19.jpg)
Comparison of algorithms (baroque)
Notes Ps13(99.33%)
Camb(98.71%)
Temp(97.67%)
LH(97.65%)
Intervals
Temp(99.45%)
Ps13(99.17%)
LH(99.16%)
Camb(98.65%)
Ints and notes
Ps13(99.25%)
Camb(98.68%)
Temp(98.56%)
LH(98.41%)
![Page 20: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/20.jpg)
Conclusion and Future Work
Algorithms based on line of fifths (L-H and Templey) mis-spelt many more notes in the classical music than other algorithms
Algorithms should be tested on more varied corpus
![Page 21: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/21.jpg)
Conclusion and Future Work
What is the best key-finding algorithm to use for pitch spelling (based on Krumhansl’s claim)
Need to determine whether or not algorithms are consistent with the perception and cognition process.
![Page 22: Pitch Spelling Algorithms](https://reader036.fdocuments.in/reader036/viewer/2022062517/568134b6550346895d9bd5c5/html5/thumbnails/22.jpg)
Thank you!