Herein, we report a computational algorithm that follows a spectroscopist-driven elucidation process of the structure of an organic molecule based on IR, ¹H and ¹³C NMR, and MS tabular data. The algorithm is independent from database searching and is based on a bottom-up approach, building the molecular structure from small structural fragments visible in spectra. It employs an analytical combinatorial approach with a graph search technique to determine the connectivity of structural fragments that is based on the analysis of the NMR spectra, to connect the identified structural fragments into a molecular structure. After the process is completed, the interface lists the compound candidates, which are visualized by the WolframAlpha computational knowledge engine within the interface. The candidates are ranked according to the predefined rules for analyzing the spectral data. The developed elucidator has a user-friendly web interface and is publicly available (http://schmarnica.si).

Troubadour platform is an open-source personalized and adaptive web platform for ear training. The platform was developed to support music theory classes with automated music-theory-related exercises. In this paper, we present our three-stage development methodology, which incorporated the needs and feedback from both teachers and students to build an engaging music-theory e-learning platform with gamification elements. We developed and evaluated the platform with students of the Conservatory of Music and Ballet Ljubljana. The students of the 1st and 2nd year of the programme were split into two groups—the control group used the traditional way of learning, while the test group augmented their learning with the Troubadour platform. The evaluation results show an increase in exam performance and corroborate the platform’s user experience as one of the key reasons for the students’ engagement.

This paper presents a new multimodal dataset Moodo that can aid the development of affective music information retrieval systems. Moodo’s main novelties are a multimodal approach that links emotional and color perception to music and the inclusion of user context. Analysis of the dataset reveals notable differences in emotion-color associations and their valence-arousal ratings in non-music and music context. We also show differences in ratings of perceived and induced emotions, especially for those with perceived negative connotation, as well as the influence of genre and user context on perception of emotions. By applying an intermediate data fusion model, we demonstrate the importance of user profiles for predictive modeling in affective music information retrieval scenarios.

Modern music streaming services rely on recommender systems to help users navigate within their large collections. Collaborative filtering (CF) methods, that leverage past user–item interactions, have been most successful, but have various limitations, like performing poorly among sparsely connected items. Conversely, content-based models circumvent the data-sparsity issue by recommending based on item content alone, but have seen limited success. Recently, graph-based machine learning approaches have shown, in other domains, to be able to address the aforementioned issues. Graph neural networks (GNN) in particular promise to learn from both the complex relationships within a user interaction graph, as well as content to generate hybrid recommendations. Here, we propose a music recommender system using a state-of-the-art GNN, PinSage, and evaluate it on a novel Spotify dataset against traditional CF, graph-based CF and content-based methods on a related song prediction task, venturing beyond accuracy in our evaluation. Our experiments show that (i) our approach is among the top performers and stands out as the most well rounded compared to baselines, (ii) graph-based CF methods outperform matrix-based CF approaches, suggesting that user interaction data may be better represented as a graph and (iii) in our evaluation, CF methods do not exhibit a performance drop in the long tail, where the hybrid approach does not offer an advantage.

We present the development and evaluation of a gamified rhythmic dictation application for music theory learning. The application was developed as a web application in the existing Troubadour platform for music ear training. The focus of the developed application was on user experience and engagement. With regards to the former, we developed a responsive and intuitive user interface; for the latter, we included several gamification elements and assessed the impact on the students’ engagement. We report on students’ experience analysis done through questionnaires and background data collected through the platform. We evaluated the rhythmic dictation application with the conservatory-level music theory students through A/B testing in order to independently evaluate the application’s impact. The results show a significant impact of the application on the students’ exam scores.

The paper presents a new compositional hierarchical model for robust music transcription. Its main features are unsupervised learning of a hierarchical representation of input data, transparency, which enables insights into the learned representation, as well as robustness and speed which make it suitable for real-world and real-time use. The model consists of multiple layers, each composed of a number of parts. The hierarchical nature of the model corresponds well to hierarchical structures in music. The parts in lower layers correspond to low-level concepts (e.g. tone partials), while the parts in higher layers combine lower-level representations into more complex concepts (tones, chords). The layers are learned in an unsupervised manner from music signals. Parts in each layer are compositions of parts from previous layers based on statistical co-occurrences as the driving force of the learning process. In the paper, we present the model’s structure and compare it to other hierarchical approaches in the field of music information retrieval. We evaluate the model’s performance for the multiple fundamental frequency estimation. Finally, we elaborate on extensions of the model towards other music information retrieval tasks.