Latent representations for traditional music analysis and generation

We create and study a generative model for Irish traditional music based on Variational Autoencoders and analyze the learned latent space trying to find musically significant correlations in the latent codes' distributions in order to perform musical analysis on data. We train two kinds of models: one trained on a dataset of Irish folk melodies, one trained on bars extrapolated from the melodies dataset, each one in five variations of increasing size. We conduct the following experiments: we inspect the latent space of tunes and bars in relation to key, time signature, and estimated harmonic function of bars; we search for links between tunes in a particular style (i.e. "reels'") and their positioning in latent space relative to other tunes; we compute distances between embedded bars in a tune to gain insight into the model's understanding of the similarity between bars. Finally, we show and evaluate generative examples. We find that the learned latent space does not explicitly encode musical information and is thus unusable for musical analysis of data, while generative results are generally good and not strictly dependent on the musical coherence of the model's internal representation.

Everybody's Talking About Jamie: a comparative analysis between the English musical and the Italian translation and its influence on the LGBTQIA+ community

“Culture has been, is and always will be useful to the political and social fight, precisely because it stirs consciences and prompts reflection”, stated Pero Di Blasio, producer of the Italian version of the musical Everybody’s Talking About Jamie in our private interview (Savoia, 2022). And the invitation for reflection mentioned by the producer represents the main topic of my dissertation, as its aim is to underline, starting from a translation point of view, the differences and similarities conveyed by the two versions of the musical, to raise awareness and spread validation towards the issues and struggles members of the LGBTQIA+ community are forced to face every day. The four chapters in which this dissertation is divided into proceed from a more generic and theoretical one (chapter 1), followed by the introduction of the musical in Chapter 2 with its British and Italian versions, contextualised in their national realities thanks to their press reviews. Then the focus will zoom into the more practical chapters, where the topic of the Italian translation will be gradually approached. The dissertation will then be concluded with the fourth chapter, where the findings identified in the third chapter will be commented, taking into consideration the audience perception and the social issues portrayed on stage by the cast of the West End musical.