2000 character limit reached
Unsupervised Learning of Harmonic Analysis Based on Neural HSMM with Code Quality Templates (2403.04135v1)
Published 7 Mar 2024 in cs.AI
Abstract: This paper presents a method of unsupervised learning of harmonic analysis based on a hidden semi-Markov model (HSMM). We introduce the chord quality templates, which specify the probability of pitch class emissions given a root note and a chord quality. Other probability distributions that comprise the HSMM are automatically learned via unsupervised learning, which has been a challenge in existing research. The results of the harmonic analysis of the proposed model were evaluated using existing labeled data. While our proposed method has yet to perform as well as existing models that used supervised learning and complex rule design, it has the advantage of not requiring expensive labeled data or rule elaboration. Furthermore, we also show how to recognize the tonic without prior knowledge, based on the transition probabilities of the Markov model.
- T.-P. Chen and L. Su. Harmony Transformer: Incorporating Chord Segmentation into Harmony Recognition. In Proceedings of the 20th International Society for Music Information Retrieval Conference, pages 259–267, 2019.
- T.-P. Chen and L. Su. Attend to chords: Improving harmonic analysis of symbolic music using transformer-based models. Transactions of the International Society for Music Information Retrieval, 4(1):1–13, 2021.
- M. S. Cuthbert and C. Ariza. music21: A toolkit for computer-aided musicology and symbolic music data. In Proceedings of the 11th International Society for Music Information Retrieval Conference, 2010.
- G. D. Forney. The viterbi algorithm. Proceedings of the IEEE, 61(3):268–278, 1973.
- M. Granroth-Wilding and M. Steedman. Statistical parsing for harmonic analysis of jazz chord sequences. In International Computer Music Conference, pages 478–485, 2012.
- R. Groves. Automatic harmonization using a hidden semi-markov model. In AIIDE Workshop, pages 48–54, 2013.
- S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural computation, 9(8):1735–1780, 1997.
- D. Hu and L. K. Saul. A Probabilistic Topic Model for Unsupervised Learning of Musical Key-Profiles. In Proceedings of the 10th International Society for Music Information Retrieval Conference, pages 441–446, 2009.
- A tutorial on deep latent variable models of natural language. arXiv preprint arXiv:1812.06834, 2018.
- D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations, 2015.
- C. L. Krumhansl. Cognitive foundations of musical pitch. Oxford University Press, 2001.
- K. Masada and R. Bunescu. Chord recognition in symbolic music: A segmental crf model, segment-level features, and comparative evaluations on classical and popular music. Transactions of the International Society for Music Information Retrieval, 2(1):1–13, 2019.
- Discovering discrete latent topics with neural variational inference. In Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 2410–2419, 06–11 Aug 2017.
- Not all roads lead to rome: Pitch representation and model architecture for automatic harmonic analysis. Transactions of the International Society for Music Information Retrieval, 3(1):42–54, 2020.
- A deep learning method for enforcing coherence in Automatic Chord Recognition. In Proceedings of the 22nd International Society for Music Information Retrieval Conference, pages 443–451, 2021.
- The pagerank citation ranking: Bring order to the web. Technical report, Stanford University, 1998.
- L. R. Rabiner. A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2):257–286, 1989.
- D. P. Radicioni and R. Esposito. BREVE: An HMPerceptron-Based Chord Recognition System. In Advances in Music Information Retrieval, pages 143–164. Springer Berlin Heidelberg, 2010.
- C. Raphael and J. Stoddard. Harmonic analysis with probabilistic graphical models. In Proceedings of the 4th International Conference on Music Information Retrieval, 2003.
- M. Rohrmeier. Towards a generative syntax of tonal harmony. Journal of Mathematics and Music, 5(1):35–53, 2011.
- R. Serfozo. Basics of applied stochastic processes. Springer, 2009.
- D. Temperley. An Algorithm for Harmonic Analysis. Music Perception, 15(1):31–68, 10 1997.
- D. Temperley. What’s Key for Key? The Krumhansl-Schmuckler Key-Finding Algorithm Reconsidered. Music Perception, 17(1):65–100, 10 1999.
- D. Temperley. The Cognition of Basic Musical Structures. The MIT Press, 2004.
- D. Temperley and D. Sleator. The melisma music analyzer. https://www.link.cs.cmu.edu/music-analysis/.
- D. Temperley and D. Sleator. Modeling meter and harmony: A preference-rule approach. Computer Music Journal, 23(1):10–27, 1999.
- Unsupervised neural hidden markov models. In Proceedings of the Workshop on Structured Prediction for NLP, pages 63–71, 2016.
- Function- and rhythm- aware melody harmonization based on tree-structured parsing and split-merge sampling of chord sequences. In Proceedings of 18th International Society for Music Information Retrieval Conference, pages 502–508, 2017.
- Y. Uehara. Unsupervised Recognition of Chords, Functions, and Tonality. PhD thesis, Japan Advanced Institute of Science and Technology, 2022.
- Y. Uehara and S. Tojo. Chord function recognition as latent state transition. SN Computer Science, 3:508, 2022.
- Y.-S. Wang and H. Wechsler. Musical keys and chords recognition using unsupervised learning with infinite gaussian mixture. In Proceedings of the 2nd ACM International Conference on Multimedia Retrieval. Association for Computing Machinery, 2012.
- S.-Z. Yu. Hidden semi-Markov models. Artificial intelligence, 174(2):215–243, 2010.
- S.-Z. Yu and H. Kobayashi. An efficient forward-backward algorithm for an explicit-duration hidden Markov model. IEEE signal processing letters, 10(1):11–14, 2003.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.