Category Archives: Music Syntax Theory

Rodrigo Schramm: Automatic transcription of a cappella recordings from multiple singers

When: Thursday 30th March, 2017 @ 5:10 PM

Where: Room 4.31/4.33, Informatics Forum, University of Edinburgh

Seminar Title

Automatic transcription of a cappella recordings from multiple singers

Seminar Speaker

Rodrigo Schramm (Visiting Fellow, C4DM, Queen Mary University of London // Federal University of Rio Grande do Sul (UFRGS), Brazil)

Seminar Abstract

This research focuses on a new method for multi-pitch detection and voice assignment applied to automatic music transcription of a cappella performances with multiple singers.

Our technique uses Probabilistic Latent Component Analysis (PLCA) for spectrogram factorisation, with the help of a 6-dimensional sparse dictionary which contains spectral templates of vowel vocalisations. A post-processing step is proposed to remove false positive pitch detections through a binary classifier, where overtone-based features are used as input into this step.

Preliminary experiments have shown promising multi-pitch detection results when applied to audio recordings of Bach Chorales and Barbershop music. Comparisons made with alternative methods have shown that our approach increases the number of true positive pitch detections while the post-processing step keeps the number of false positives lower than those measured in comparative approaches. Voice assignment is driven by the integration of an HMM-based method into the PLCA model, improving concomitantly the accuracy of multi-pitch detection and voice separation.

Speaker Bio

Rodrigo Schramm received his PhD in Computer Science from the Federal University of Rio Grande do Sul (UFRGS)/Brazil in 2015, where he is currently a faculty member. Between 2013 and 2014, he was visiting fellow at ICCMR – Interdisciplinary Centre for Computer Music Research – Plymouth University/UK. In 2016, he was awarded by the Royal Academy of Engineering with the Newton Research Collaboration Programme Award. Currently, he is conducting research at the C4DM (QMUL) in London, focusing his activities on the development of techniques for automatic transcription of audio recordings containing multiple singers.

Bastiaan van der Weij: Modelling meter perception in music with predictive coding and perceptual inference

When: Wednesday 18th November, 2015 @ 5:10 PM

Where: Room 4.31/4.33, Informatics Forum, University of Edinburgh

Seminar Title

Modelling meter perception in music with predictive coding and perceptual inference.

Seminar Speaker(s)

Bastiaan van der Weij (University of Amsterdam)

Seminar Abstract

Meter perception plays an important role in human musicality. An increasing number of studies show that meter perception is influenced by enculturation. Additionally, ethnomusicological literature has described a number of cases where individuals from different cultures have systematically different metrical interpretations of certain rhythms. Current models of rhythm perception do not account satisfactorily for effects of enculturation.

We propose an account of meter perception based on predictive coding and perceptual inference. We formally define our hypothesis, and provide a computational implementation. We model perception by activating patterns of expectation, categorised in terms of probabilistic hypotheses about candidate metrical interpretations and learned from a large collection of rhythms, proportional to how efficiently they encode the observed rhythm.

Our approach is based on an already successful model of musical expectation, which we extend to incorporate perceptual inference. Through evaluation on a corpus of artificially generated rhythms, we show that the model can, in principle, explain differences in perceived meter in terms of learning through previous exposure.

Speaker Bio

Undergratuate degree: Artificial Intelligence, University of Amsterdam

Postgraduate degree: Cognitive Science, University of Edinburgh

My master’s thesis with Mark Steedman was an attempt at using a chart-parser to parse rhythmic structure in jazz performances. Inspired by that, I applied for a PhD position at the Institute for Logic, Language and Computation back in Amsterdam, where I’m now doing a PhD supervised by Henkjan Honing and, as of recently, co-supervised by Marcus Pearce. Currently, I’m visiting Marcus at QMUL. The goal of the visit is to merge my model of metrical interpretation with his IDyOM model.

Mark Granroth-Wilding: Parsing Jazz: Harmonic Analysis of Music Using Combinatory Categorial Grammar

When: June 19, 2013 @ 5:30 PM – 6:30 PM

Where: Room 2.33, Informatics Forum, Crichton Street, University of Edinburgh

Seminar Title

Parsing Jazz: Harmonic Analysis of Music Using Combinatory Categorial Grammar

Seminar Speaker(s)

Dr Mark Granroth-Wilding (ILCC, School of Informatics, University of Edinburgh)

Seminar Abstract

In Western tonal music, an important part of a listener’s understanding of a piece of music is an unconcious analysis of the harmonic progression underlying it. Harmonic progressions in tonal music have been described as having a hierarchical structure, similar to that found in the syntax and semantics of natural language. This work demonstrates the use of grammar-based parsing, with related machine-learning techniques, as used in Natural Language Processing, for automatic analysis of the structure of jazz chord sequences, according to a theory in the tradition of functional harmonic analysis.

This talk will examine the theory of harmonic structure underlying the work and introduce a grammar formalism suitable for processing the syntax of tonal harmony. It will then address the practical problem of of automatic harmonic analysis by adapting some statistical parsing techniques from natural language processing. The results of parsing experiments indicate that the constraints of a grammar help in recovering harmonic analyses, when compared with a Markovian approach.

Martin Rohrmeier: Musical Syntax and Its Cognitive Implications

When: December 6, 2012 @ 5:30 PM – 6:30 PM

Where: Room 4.33, Informatics Forum, Crichton Street, University of Edinburgh

Seminar Title

Musical Syntax and Its Cognitive Implications

Seminar Speaker(s)

Dr Martin Rohrmeier

Seminar Abstract

In recent years, the cognitive link between music and language has been subject to various debates across disciplines ranging from linguistics, music, psychology, computer science, up to evolution and anthropology (e.g. Patel, 2008; Rebuschat, Rohrmeier, Cross & Hawkins, 2011). One particular domain, in which an overlap between music and language has been frequently discussed, concerns the principles of syntactic structure building. In this talk I will present a formal approach to musical syntax that grounds on earlier work by Mark Steedman (1996) and the cognitive model by Lerdahl & Jackendoff (1983). The theory proposes an explicit, general set of generative rules to describe principles of tonal harmony (Rohrmeier, 2011). It further characterises ways in which tonal music is recursive and casts empirical (cognitive) predictions. I will give an introduction into musical syntax and what it means to *hear* musical dependencies and tree structures. I will further relate the formalism to recent computational approaches and findings from cognitive research.

Granroth-Wilding, M & Steedman, M. (2012) Statistical Parsing for Harmonic Analysis of Jazz Chord Sequences. In Proceedings of the International Computer Music Conference (ICMC).
Haas, W.B. de, Rohrmeier, M., Veltkamp, R.C. & Wiering, F. (2009). Modeling Harmonic Similarity Using a Generative Grammar of Tonal Harmony. In Proceedings of theInternational Conference on Music Information Retrieval (ISMIR).
Lerdahl, F. & Jackendoff, R. (1983). A Generative Theory of Tonal Music. Cambridge, MA.
Patel, A.D. (2008). Music, Language, and the Brain. Oxford University Press, New York.
Rebuschat, P., Rohrmeier, M., Cross, I., Hawkins (2011) Eds. Language and Music as Cognitive Systems. Oxford University Press
Rohrmeier, M. (2011). Towards a generative syntax of tonal harmony. Journal of Mathematics and Music, 5 (1), pp. 35-53.
Steedman, M. (1996). The Blues and the Abstract Truth: Music and Mental Models. In A. Garnham and J. Oakhill, (eds.), Mental Models In Cognitive Science. Mahwah, NJ: Erlbaum, 305-318.

Presentation Slides

PDF Document (2MB)