Transcription of music could be defined as an act of listening to a piece of music and writing down music notation for the piece. Transcription of polyphonic music (polyphonic pitch recognition) converts an acoustical waveform into a parametric representation, where notes, their pitches, starting times and durations are extracted from the signal.
SONIC is our system for transcription of polyphonic piano music. The system takes an acoustical waveform of a piano recording (.wav format, 44.1 kHz sampling rate, 16 bit resolution, mono) as its input. Stereo recordings should be converted to mono before use. The output of the system is a MIDI file containing the transcription. Notes, their starting times, durations and loudness' are extracted from the signal.
Implementation details
SONIC is based on a connectionist paradigm; neural networks are used for partial tracking, note recognition, onset detection and detection of repeated notes.
For more details, see the following publications:
- M. Marolt, A connectionist model of finding partial groups in music recordings with application to music transcription, In: Ribiero et al (eds.). Adaptive and natural computing algorithms : proceedings of the International Conference in Coimbra, Portugal, 2005. Wien; New York: Springer, cop. 2005, pp. 494-497, 2005.
- M. Marolt, A connectionist approach to automatic transcription of polyphonic piano music, IEEE Transactions on Multimedia, 2004, Vol. 6, no. 3, pp. 439-449, 2004.
- M. Marolt, Networks of adaptive oscillators for partial tracking and transcription of music recordings, Journal of New Music Research, 2004, vol. 33, no. 1, pp. 49-59, 2004.
- M. Marolt, S. Divjak, On detecting repeated notes in piano music, in Proceedings of ISMIR 2002, Paris, France, 2002.
- M. Marolt, A. Kavcic, M. Privosnik, Neural Networks for Note Onset Detection in Piano Music. Unpublished, 2002.
- M. Marolt, A. Kavcic, M. Privosnik , On detecting note onsets in piano music, Proceedings of MELECON 2002, Cairo, Egypt, 2002.
- M. Marolt, SONIC : transcription of polyphonic piano music with neural networks, Proceedings of Workshop on Current Research Directions in Computer Music, Barcelona, Spain, November 15-17, 2001.
- M. Marolt, M. Privosnik, SONIC : a system for transcription of piano music, in Kluev, V., D'Attelis, C. E., Mastorakis, N. E. (eds.), Advances in automation, multimedia and video systems and modern computer science, WSES Press, cop. 2001.
- M. Marolt, Adaptive oscillator networks for partial tracking and piano music transcription, Proceedings of the 2000 International Computer Music Conference, Berlin, Germany, 27 August - 1 September 2000.
- M. Marolt, Transcription of polyphonic piano music with neural networks, Proceedings Melecon Vol. 2, Signal and image processing, Cyprus, May 29-31, 2000.
- M. Marolt, A comparison of feed forward neural network architectures for piano music transcription, Proceedings of the 1999 International Computer Music Conference, Beijing, China, 1999.
Transcription examples
Synthesised recordings
Transcriptions of recordings synthesised from MIDI files with various piano samples.
- J.S. Bach, Two part invention
no. 13 in A minor, BWV784
Source Transcription Resynthesis - J.S. Bach, Partita no.
4 in D major, BWV828
Source Transcription Resynthesis - J.S. Bach, English suite
no. 5 in E minor, BWV810, 1. mvm.
Source Transcription Resynthesis - D. Scarlatti, Sonata in
Eb major K. 371
Source Transcription Resynthesis - W.A. Mozart, Sonata no.
15 in C major, K. 545, 3. mvm.
Source Transcription Resynthesis - W.A. Mozart, Sonata no.
13 in B major, K. 333, 1. mvm.
Source Transcription Resynthesis - A. Dvorak, Humoresque
no. 7, op. 101
Source Transcription Resynthesis - P.I. Cajkovski, Uverture
from The Nutcracker
Source Transcription Resynthesis - P.I. Cajkovski, Waltz
of the Flowers from The Nutcracker
Source Transcription Resynthesis - S. Joplin, The Entertainer
Source Transcription Resynthesis - S. Joplin and S. Hayden,
Kismet Rag
Source Transcription Resynthesis - D. Fingers, Thirty Minute
Woman
Source Transcription Resynthesis
Real Piano music recordings
Transcriptions of real recordings taken from CDs.
- J.S. Bach, Goldberg variations,
BWV988, variation no. 10, performer Andrei Gavrilov, Deutsche Grammophon
463 019-2
Source Transcription Resynthesis - J.S. Bach, English suite
no. 5 in E minor, BWV810, 1. mvm., performer Murray Perahia, Sony
Classical SK 60277
Source Transcription Resynthesis - L.V. Beethoven, Sonata
no. 14 op. 27/2 (Moonlight), 2. mvm., performer Wilhelm Kempff, Deutsche
Grammophon 415 834-2
Source Transcription Resynthesis - R. Schumman, Träumerei,
perf. Cyprien Katsaris, TELDEC 75863
Source Transcription Resynthesis - F. Chopin, Nocturne no.
2 in Eb minor, Op. 9/2, performer Artur Rubinstein, RCA: 60822
Source Transcription Resynthesis - S. Joplin, The Entertainer,
performer unknown, MCA 11836
Source Transcription Resynthesis - J. Kern and O. Hammerstein,
All the Things You Are, performer Bill Evans, Milestone MCD-9195-2
Source Transcription Resynthesis - M. Dixon, R. Henderson,
Bye Bye Blackbird (intro), performer Oscar Peterson, MPS 821 843-2
Source Transcription Resynthesis - M. Dixon, R. Henderson,
Bye Bye Blackbird (solo), performer Oscar Peterson, MPS 821 843-2
Source Transcription Resynthesis
Other non-piano recordings
SONIC is designed to transcribe solo piano music. How does it fare with other recordings?
- A.C. Jobim, Saudade do
Brasil, performed by Bill Evans (piano), Eddie Gomez (bass), Fantasy
OJCCD-814-2
Source Transcription Resynthesis - J.S. Betty, C.A. Green,
Just In Time, performed by Oscar Peterson (piano), Ray Brown (bass),
Ed Thigpen (drums), Verve 852 769-2
Source Transcription Resynthesis - O. Lopez, Classical Soul,
perf. Oscar Lopez (guitar), Narada 61065
Source Transcription Resynthesis - C. Atkins, Acoustic Guitar
Medley, perf. Chet Atkins (guitar), ??
Source Transcription Resynthesis - P. Desmond, Take Five,
performed by Dave Brubeck (piano), Paul Desmond (alto saxophone),
Eugene Wright (bass), Joe Morello (drums), Columbia/Legacy CK 65122
Source Transcription Resynthesis - T. Monk,
Thelonious, performed by Thelonious Monk (piano), Idrees Sulieman
(trumpet), Danny Quebec West (alto sax), Billy Smith (tenor sax),
Gene Ramey (bass), Art Blakey (drums), Blue Note CDP 7243 8 30363
2 5
Source Transcription Resynthesis - A. Piazzolla, Invierno
Porteno, performed by Astor Piazzola (bandoneon), Antonio Agri (viola),
Oscaldo Manzi (piano), Cacho Tirao (el. guitar), Kicho Diaz (bass),
BMG 74321 21373-2
Source Transcription Resynthesis - L. Brown, S. Stept, C.
Tobias, Comes Love, performed by Billie Holiday (vocals), Harry Edison
(trumpet), Ben Webster (tenor sax), Jimmy Rowles (piano), Barney Kessel
(el. g.), Red Mitchell (bass), Gus Johnson (drums), Verve 314 513
943-2
Source Transcription Resynthesis