Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

An Improved Automatic Music Transcription Method Using TV-Filter and Optimal Note Combination

TV-필터와 최적 음표조합을 이용한 개선된 가변템포 음악채보방법

  • Ju, Young-Ho (Division of Computer Science & Engineering, Chonbuk National University) ;
  • Lee, Joonwhoan (Division of Computer Science & Engineering, Chonbuk National University)
  • 주영호 (전북대학교 전자정보공학부 컴퓨터공학전공) ;
  • 이준환 (전북대학교 전자정보공학부 컴퓨터공학전공)
  • Received : 2013.01.21
  • Accepted : 2013.04.11
  • Published : 2013.08.25
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes three methods for improving the accuracy of auto-music transcription considering with time-varying tempo from monophonic sound. The first one that uses TV(Total Variation) filter for smoothing the pitch data reduces the fragmentation in the pitch segmentation result. Also, the measure finding method that combines three different ways based on pitch and energy of sound data, respectively as well as based on rules produces more stable result. In addition the temporal result of note-length encoding is corrected in optimal way that the resulted encoding minimizes the sum of quantization error in a measure while the sum of note-lengths is equal to the number of beats. In the experiment with 16 children songs, we obtained the improved result in which measure finding was complete, the accuracy of encoding for note-length and pitch was about 91.3 and 86.7, respectively.

본 논문에서는 가변템포를 반영한 단일음악 채보의 정확성을 증가시키기 위한 기존의 방법을 개선하는 세 가지 방안을 제시하였다. 첫째는 TV 필터를 활용한 음정 데이터의 평활화로 음정분할 결과의 파편화 현상이 줄어들게 하였다. 또한 음정과 에너지, 규칙기반 방법을 융합한 마디탐색 방법으로 마디 탐색결과의 안정성을 향상시켰다. 뿐만 아니라 마디 내에서 음표의 합이 박자수와 같으면서 양자화 오차의 합을 최소화하는 최적의 방법으로 임시 음길이 부호화 결과를 보정하였다. 그 결과 16개의 동요 음원에서 완벽한 마디위치를 탐색하였으며, 음길이 부호의 정확도 약 91.3%, 음정 부호화 정확도는 약 86.7%의 개선된 결과를 얻을 수 있었다.

Keywords

References

  1. Matija Marolt and Marko Privosnik, "SONIC : A System for Transcription of Piano Music," Cybernetics and Systems, Vol.33, No.6, pp.603-627, 2002. https://doi.org/10.1080/01969720290040777
  2. Martin, "A Blackboard System for Automatic Transcription of Simple Polyphonic Music," MIT Media Laboratory Perceptual Computing Section Technical Report No.385, 1996.
  3. Marolt, "A Connectionist Approach to Automatic Transcription of Polyphonic Piano Music," IEEE Transactions on Multimedia, Vol. 6, No.3, pp.439-449, 2004. https://doi.org/10.1109/TMM.2004.827507
  4. Jung-yeong Jang, Design and Implementation of Song Recognition System using Fuzzy Integral, KAIST, Master Thesis, 1996.
  5. Ayoung Heung, Joonwhoan Lee, "Automatic Music Transcription System Using SIDE and Genetic Algorithm," Journal of Korea Information Processing Society, Vol.16, No.2, 2009.
  6. Eungjong Park, Songyi Sin, Joonwhaon Lee, "Finding Measure Position Using Combination Rules of Musical Notes in Monophonic Song," Journal of The Korea Contents Association, Vol.9, No.10, pp.1-12, 2009.
  7. Jeonggyu Ji, "Melodic query processor for effieient retrieval of an audio database," Soongsil University, PhD Thesis, 1998.
  8. Geoffroy Peeters, "Time Variable Tempo Detction and Beat Marking," International Computer Music Association, Barcelona, Spain, 2005.
  9. Kenichi Miyamoto, Hirokazu Kameoka, Haruto Takeda, Takuya Nishimoto, and Shigeki Sagayama, "Probailistic Approach to Automatic Music Transcription from Audio Signals," Proceedings of IEEE Conf. on ASSP, Vol.2, pp.II-697-700, April 2007.
  10. Youngho Ju, Baniya Babukaji, Joonwhoan Lee, "Automatic Music Transcription Considering Time-Varying Tempo," Journal of The Korea Contents Association, Vol.12, No.11, pp.9-19, 2012. https://doi.org/10.5392/JKCA.2012.12.11.009
  11. Ivan W. Selesnick and Ilker Bayram, "Total Variation Filtering", Availavle: http://eeweb.poly.edu/iselesni/lecture_notes/TV_fi ltering.pdf, Fabruary, 2010, [Accessed: January 14, 2013].
  12. Scott Shaobing Chen and P. S. Gopalakrishnan, Speaker, "Environment and Channel Change Detection and Clustering via The Bayesian Information Criterion," DARPA Broadcast News Transcription and Understanding Workshop, 1998.
  13. Praat, Available: http://www.praat.org, [Accessed: January 14, 2013].
  14. Ilua Pollak, Alan S. Willsky and Hamid Krim, "Image Segmentation and Edge Enhancement with Stabilized Inverse Diffusion Equations", IEEE Transactions on Image Processing, Vol. 9, No.2, pp.256-266, 2000. https://doi.org/10.1109/83.821738
  15. Korean Society for Music Perception and Cognition, Perseption and Congnition of Music, Eumaksekye, 2005.