Approximate Nearest Neighbour-based Index Tree:  A Case Study for Instrumental Music Search

Nguyen, Hai Thanh; Vo, Linh Dan; Tran, Thien Thanh

doi:10.2478/acss-2023-0015

Abstract

Many people are interested in instrumental music. They may have one piece of song, but it is a challenge to seek the song because they do not have lyrics to describe for a text-based search engine. This study leverages the Approximate Nearest Neighbours to preprocess the instrumental songs and extract the characteristics of the track in the repository using the Mel frequency cepstral coefficients (MFCC) characteristic extraction. Our method digitizes the track, extracts the track characteristics, and builds the index tree with different lengths of each MFCC and dimension number of vectors. We collected songs played with various instruments for the experiments. Our result on 100 pieces of various songs in different lengths, with a sampling rate of 16000 and a length of each MFCC of 13, gives the best results, where accuracy on the Top 1 is 36 %, Top 5 is 4 %, and Top 10 is 44 %. We expect this work to provide useful tools to develop digital music e-commerce systems.

References

R. Ernst, “Music for life,” Music Educators Journal, vol. 88, no. 1, pp. 47–51, Jul. 2001. https://doi.org/10.2307/3399777
Search in Google Scholar Back to article
C. Jordan, “When i’m 64: A review of instrumental music-making and brain health in later life,” Experimental Gerontology, vol. 123, pp. 17–23, Aug. 2019. https://doi.org/10.1016/j.exger.2019.05.006
Search in Google Scholar Back to article
G. Johnson, D. Otto, and A. A. Clair, “The effect of instrumental and vocal music on adherence to a physical rehabilitation exercise program with persons who are elderly,” Journal of Music Therapy, vol. 38, no. 2, pp. 82–96, Jul. 2001. https://doi.org/10.1093/jmt/38.2.82
Search in Google Scholar Back to article
L. Chaddock-Heyman, P. Loui, T. B. Weng, R. Weisshappel, E. McAuley, and A. F. Kramer, “Musical training and brain volume in older adults,” Brain Sciences, vol. 11, no. 1, Jan. 2021, Art. no. 50. https://doi.org/10.3390/brainsci11010050
Search in Google Scholar Back to article
A. Creech, S. Hallam, H. McQueen, and M. Varvarigou, “The power of music in the lives of older adults,” Research Studies in Music Education, vol. 35, no. 1, pp. 87–102, Mar. 2013. https://doi.org/10.1177/1321103x13478862
Search in Google Scholar Back to article
K. L. Hyde, J. Lerch, A. Norton, M. Forgeard, E. Winner, A. C. Evans, and G. Schlaug, “The effects of musical training on structural brain development,” Annals of the New York Academy of Sciences, vol. 1169, no. 1, pp. 182–186, Jul. 2009. https://doi.org/10.1111/j.1749-6632.2009.04852.x
Search in Google Scholar Back to article
R. Román-Caballero, M. A. Vadillo, L. J. Trainor, and J. Lupiáñez, “Please don’t stop the music: A meta-analysis of the cognitive and academic benefits of instrumental musical training in childhood and adolescence,” Educational Research Review, vol. 35, Feb. 2022, Art. no. 100436. https://doi.org/10.1016/j.edurev.2022.100436
Search in Google Scholar Back to article
C. Janiesch, P. Zschech, and K. Heinrich, “Machine learning and deep learning,” Electronic Markets, vol. 31, no. 3, pp. 685–695, Apr. 2021. https://doi.org/10.1007/s12525-021-00475-2
Search in Google Scholar Back to article
M. Chapparband, M. G. Kulkarni, D. K. Sameeksha, A. V. Krishna, and A. Bhat, “Shruti detection using machine learning and sargam identification for instrumental audio,” in Advances in Speech and Music Technology. Advances in Intelligent Systems and Computing, A. Biswas, E. Wennekes, T.P. Hong, and A. Wieczorkowska, Eds., vol 1320. Springer, Singapore, 2021, pp. 145–156. https://doi.org/10.1007/978-981-33-6881-1_13
Search in Google Scholar Back to article
A. Huaysrijan and S. Pongpinigpinyo, “Deep convolution neural network for Thai classical music instruments sound recognition,” in 2021 25th International Computer Science and Engineering Conference (ICSEC), Chiang Rai, Thailand, Nov. 2021, pp. 283–288. https://doi.org/10.1109/icsec53205.2021.9684611
Search in Google Scholar Back to article
W. Han, C.-F. Chan, C.-S. Choy, and K.-P. Pun, “An efficient MFCC extraction method in speech recognition,” in 2006 IEEE International Symposium on Circuits and Systems, Kos, Greece, May 2006. https://doi.org/10.1109/iscas.2006.1692543
Search in Google Scholar Back to article
M. A. Hossan, S. Memon, and M. A. Gregory, “A novel approach for MFCC feature extraction,” in 2010 4th International Conference on Signal Processing and Communication Systems, Gold Coast, QLD, Australia, Dec. 2010, pp. 1–5. https://doi.org/10.1109/icspcs.2010.5709752
Search in Google Scholar Back to article
Y. Liu, Y. Yin, Q. Zhu, and W. Cui, “Musical instrument recognition by XGBoost combining feature fusion,” arXiv, Jun. 2022. [Online]. Available: https://arxiv.org/abs/2206.00901
Search in Google Scholar Back to article
Y. H. Dandawate, P. Kumari, and A. Bidkar, “Indian instrumental music: Raga analysis and classification,” in 2015 1st International Conference on Next Generation Computing Technologies (NGCT), Dehradun, India, Sep. 2015, pp. 725–729. https://doi.org/10.1109/ngct.2015.7375216
Search in Google Scholar Back to article
A. Ghosal, R. Chakraborty, B. C. Dhara, and S. K. Saha, “Song/instrumental classification using spectrogram based contextual features,” in CUBE’12: Proceedings of the CUBE International Information Technology Conference, ACM Press, Sep. 2012, pp. 21–25. https://doi.org/10.1145/2381716.2381722
Search in Google Scholar Back to article
R. Raguram, J.-M. Frahm, and M. Pollefeys, “A comparative analysis of RANSAC techniques leading to adaptive real-time random sample consensus,” in Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, D. Forsyth, P. Torr, and A. Zisserman, Eds., vol 5303. Springer, Berlin, Heidelberg, 2008, pp. 500–513. https://doi.org/10.1007/978-3-540-88688-4_37
Search in Google Scholar Back to article
S. M. Elghamrawy and S. E. Ibrahim, “Audio signal processing and musical instrument detection using deep learning techniques,” in 2021 9th International Japan-Africa Conference on Electronics, Communications, and Computations (JAC-ECC). Alexandria, Egypt, Dec. 2021, pp. 146–149. https://doi.org/10.1109/jac-ecc54461.2021.9691427
Search in Google Scholar Back to article
K. O’Shea and R. Nash, “An introduction to convolutional neural networks,” arXiv, 2015. [Online]. Available: https://arxiv.org/abs/1511.08458
Search in Google Scholar Back to article
F. Murtagh, “Multilayer perceptrons for classification and regression,” Neurocomputing, vol. 2, no. 5–6, pp. 183–197, Jul. 1991. https://doi.org/10.1016/0925-2312(91)90023-5
Search in Google Scholar Back to article
A. Sherstinsky, “Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network,” Physica D: Nonlinear Phenomena, vol. 404, Mar. 2020, Art. no. 132306. https://doi.org/10.1016/j.physd.2019.132306
Search in Google Scholar Back to article
B. McFee et al., “librosa/librosa: 0.10.0.post2,” Mar. 2023. [Online]. Available: https://zenodo.org/record/591533
Search in Google Scholar Back to article
J. Lyons et al., “jameslyons/python speech features: release v0.6.1,” Jan. 2020. [Online]. Available: https://zenodo.org/record/3607820
Search in Google Scholar Back to article
E. Bernhardsson, “Annoy: Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk,” Python package version 1.17.3, Jun. 2023. [Online]. Available: https://pypi.org/project/annoy/
Search in Google Scholar Back to article
P. V. Toan, “Xay dung he thong tim kiem nhac bang am thanh voi Python va Approximate Nearest Neighbors,” 2018. [Online]. Available: https://viblo.asia/p/xay-dung-he-thong-tim-kiem-nhac-bang-am-thanhvoi-python-va-approximate-nearest-neighbors-924lJbXWlPM
Search in Google Scholar Back to article
T. B. Arnold, “kerasR: R interface to the Keras deep learning library,” The Journal of Open Source Software, vol. 2, no. 14, Jun. 2017, Art. no. 296. https://doi.org/10.21105/joss.00296
Search in Google Scholar Back to article

Approximate Nearest Neighbour-based Index Tree: A Case Study for Instrumental Music Search

Abstract

Paradigm

My account