FIGURE 1 - available via license: CC BY
Content may be subject to copyright.
| Extract of Schubert's lied "Der Doppelgänger" (Henrich Heine). Chords in a chord progression are not independent from each other but are linked according to musical rules or musical ideas. An example of such musical idea is shown in the work of Mishkin (1978), who analyzes that Schubert employs in some lieder of his last year harmonic parallelism between triads a half step apart when the poetic images evoke the supernatural. Mishkin provides an example with "Der Doppelgänger" where "the vocal line is supported by hollow sonorities in the piano accompaniment to suggest the dreamlike horror of beholding one's own double weeping before the house of the departed beloved. The hallucinatory impression is intensified, in the concluding passage for piano alone (Indicated by the blue line in this figure), through an organum-like progression that moves in parallel motion through a triad on the lowered supertonic degree".
Source publication
Within the last 15 years, the field of Music Information Retrieval (MIR) has made tremendous progress in the development of algorithms for organizing and analyzing the ever-increasing large and varied amount of music and music-related data available digitally. However, the development of content-based methods to enable or ameliorate multimedia retr...
Contexts in source publication
Context 1
... general, the set of variables X ∪ Y has a complex structure. For example, chords in a chord progression are not independent from each other: they are linked according to complex musical rules or musical ideas (see the example in Figure 1). Observations are also linked according to the underlying states they represent (see Figure 2, left). ...
Context 2
... 5th line shows the results obtained with a baseline chord HMM, considering only chroma observation and transitions between successive chords. The last line shows the results obtained with a model that adds long-term chord dependencies: it favors same chord progressions for all instances of the same segment type (see the corresponding graphical model in Figure 11 below). The ground-truth chord of the first bar of the verse is an Em chord. ...
Context 3
... deep transfer learning, the knowledge to be transferred is the relationship among the data. For instance we could use knowledge learned in the movie industry to help solve tasks in the music domain (see Figure 10). These directions are steps toward designing a generalized framework for music processing that can discover its own representations at once, as humans do, and is able to integrate prior knowledge. ...
Context 4
... model proposed for automatic chord estimation in Papadopoulos and Tzanetakis (2017) is depicted in Figure 11. ...
Context 5
... structure of the domain is represented by a set of weighted logical formulas (described by the sentences F 1 , . . . , F 5 in Figure 11). The constants of the domain are the 24 major and minor triads, and the 24 major and minor keys. ...
Context 6
... constants of the domain are the 24 major and minor triads, and the 24 major and minor keys. The logical formulas applied to these constants produce a Markov network illustrated in Figure 11. In addition to this set of rules, a set of evidence literals represents the observations (chroma vectors) and prior information (the temporal structure). ...
Context 7
... graphical models can be specified compactly in Markov logic. For instance, in Figure 11, formulas F 1 and F 2 compactly encode the relational structure of a HMM. This model can then easily be extended to combine various kind of harmony-related information at various time-scales in a single unified formalism, by adding logical formulas and corresponding weights. ...
Context 8
... have also emphasized the need to be able to reason jointly at multiple abstraction levels and multiple time scales (see section 2.2). The model depicted in Figure 11 combines various kinds of harmony-related information (chords, global and local keys). Also, it has been possible to incorporate dependencies between music events at various time-scales (beat-synchronous analysis frame, phrase and global structure). ...
Similar publications
The aim of this paper is to analyze the effect of FEC coding of M-ary modulation (BPSK, QAM and 16-QAM) based WiMAX wireless communication system over different communication channels AWGN and fading channels (Rician) with application of digital audio transmission. FEC channel coding incorporates Reed-Solomon (RS) encoder with Convolutional encoder...
Citations
... The study of music features, distinct attributes encapsulating the essence of a piece of music, is pivotal for understanding the intricate structure of compositions and propelling the advancement of music information retrieval (MIR) technologies [1]. In the digital era, machine learning algorithms have become instrumental in MIR tasks due to their precision and efficiency in analyzing vast music datasets [17]. At the core of this technological revolution is the process of feature extraction [18]. ...
The responsible artificial intelligence (AI) paradigm requires machine learning (ML) and AI engineers to ensure transparent and interpretable intelligent models across domains. This requirement becomes even more complex and crucial when dealing with feature learning using sound data, as deriving model explainers in this context is a more detailed and sophisticated process. In this work, we demonstrate a responsible approach to AI modeling and leverage three explainable artificial intelligence (XAI) tools to derive and establish explainers for the music genre classification model-agonistically. Explain like am 5 (ELi5), Shapley Additive exPlanations (SHAP), and Local Interpretable Model-agnostic Explanations (LIME) were particularly used to interpret and simplify the model’s decision-making processes regardless of their discrete mathematical foundations. This transparency provides a deeper understanding of sound feature patterns and characteristics that inform genre classes for the models through graphical and qualitative feature contributions to explain the model’s justification. We developed convolutions neural networks (CNNs) with and without cross-validation and a vision transformer (ViT) approach utilizing MobileNets. Ultimately, the CNN with cross-validation demonstrated superior performance, achieving 80% accuracy on the test set and 84% accuracy on the validation set. This work advances the border of music intelligence research and promotes the broader cause of responsible AI to ensure that complex models remain comprehensible and accountable.
... A possible candidate for such a framework is statistical relational artificial intelligence (StarAI), where learning and logical rules coexist. I discussed this idea, together with another researcher in MIR, in a recent perspective paper that focuses on the potential that StarAI has for modelling complex musical problems (Crayencour and Cella, 2019). ...
This paper is about the story of my relationship, as a contemporary music composer, with computational tools that are situated in the areas of signal processing, machine learning and music information retrieval (MIR). I believe that sharing this story can be useful to the MIR community since it illustrates the problems that can arise when you try to use these techniques in the context of contemporary music creation. Since this is a personal story, I will refer to experiences that I had during about fifteen years of usage of MIR-related technologies. I will show how these technologies tried to (unsuccessfully) shape my musical thinking and why I believe that some of them have come to an end. Finally, I will propose new possible directions for the future of MIR.