MuseReduce: A Generic Framework for Hierarchical Music Analysis

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

There has been a growing interest in developing simulated learners to enhance learning and teaching experiences in educational environments. However, existing works have primarily focused on structured environments relying on meticulously crafted represent ...

The cortical tracking of stimulus features is a crucial neural requisite of how we process continuous music. We here tested whether cortical tracking of the beat, typically related to rhythm processing, is modulated by pitch predictability and other top-do ...

This dissertation on data-driven music theory is centered around curatorial practices concerning the creation, publication, and evaluation of large, expert-annotated symbolic datasets. With its primary interest in the harmony of European tonal music from i ...

Diachronic stylistic changes in music are to a large extent affected by composers' different choices, for example regarding the usage of tones, intervals, and harmonies. Analyzing the tonal content of pieces of music and observing them over time is thus in ...

As a universal expression of human creativity, music is capable of conveying great subtlety and complexity. Crucially, this complexity is not encoded in the score or in the sounds, but is rather construed in the mind of the listener in the form of nuanced ...

Accurate human trajectory prediction is crucial for applications such as autonomous vehicles, robotics, and surveillance systems. Yet, existing models often fail to fully leverage the non-verbal social cues human subconsciously communicate when navigating ...

Claude Debussy’s personal style is typically characterised as a departure from earlier diatonic tonality, including a greater variety of pitch-class materials organised in fragmented yet coherent compositions. Exploiting the music-theoretical interpretabil ...

The aim of this paper is to argue that complementation is an operation similarly fundamental to music theory as transposition and inversion. We focus on studying the chromatic complement mapping that translates diatonic seventh chords into 8-note scales wh ...

The human ability to perceive and understand music is remarkable. From an unstructured stream of acoustic input it creates a wide range of experiences, from psycho-acoustic effects to emotional and aesthetic responses. One such set of phenomena is the expe ...

Music can be interpreted by attributing syntactic relationships to sequential musical events, and, computationally, such musical interpretation represents an analogous combinatorial task to syntactic processing in language. While this perspective has been ...

Self-supervised learning (SSL) models use only the intrinsic structure of a given signal, independent of its acoustic domain, to extract essential information from the input to an embedding space. This implies that the utility of such representations is no ...

Recent transformer language models achieve outstanding results in many natural language processing (NLP) tasks. However, their enormous size often makes them impractical on memory-constrained devices, requiring practitioners to compress them to smaller net ...

The Python library ms3 makes scores (symbolic representations of music) operational for computational approaches by representing their contents as sets of tabular files. Music scores represent relations between sounding events by graphical means. The Free ...

Introduced to enable a wider use of Earth Observation images using natural language, Remote Sensing Visual Question Answering (RSVQA) remains a challenging task, in particular for questions related to counting. To address this specific challenge, we propos ...

Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...

The success of self-supervised learning in computer vision and natural language processing has motivated pretraining methods on tabular data. However, most existing tabular self-supervised learning models fail to leverage information across multiple data t ...

Natural language processing and other artificial intelligence fields have witnessed impressive progress over the past decade. Although some of this progress is due to algorithmic advances in deep learning, the majority has arguably been enabled by scaling ...

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

Recent successes in deep learning for vision and natural language processing are attributed to larger models but come with energy consumption and scalability issues. Current training of digital deep-learning models primarily relies on backpropagation that ...

Functional harmony is an integral part of many repertoires in the Western musical practices, including both diatonic and extended tonality. In the latter context, music-theoretical accounts suggest that the three octatonic equivalence classes (OECs) consis ...

MuseReduce: A Generic Framework for Hierarchical Music Analysis

Chat with Graph Search

PharmaSimText: A Text-Based Educational Playground filled with RL-LLM Agents That Work Together Even in Disagreement

Cortical and behavioral tracking of rhythm in music: Effects of pitch predictability, enjoyment, and expertise

Data-Driven Music Theory: Curating and Investigating Large Corpora of Digitally Encoded Music Analyses

Computational modeling of interval distributions in tonal space reveals paradigmatic stylistic changes in Western music history

Hearing structure in music: An empirical inquiry into listening as representation and processing

Social-Transmotion: Promptable Human Trajectory Prediction

The diachronic development of Debussy’s musical style: a corpus study with Discrete Fourier Transform

Fishing for complements with chord, scale, and rhythm nets

The Structure of Free Polyphony

Interpreting Rhythm as Parsing: Syntactic-Processing Operations Predict the Migration of Visual Flashes as Perceived During Listening to Musical Rhythms

Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?

Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models

ms3: A parser for MuseScore files, serving as data factory for annotated music corpora

Multi-task prompt-RSVQA to explicitly count objects on aerial images

Modeling Structured Data in Attention-based Models

XTab: Cross-table Pretraining for Tabular Transformers

Text Representation Learning for Low Cost Natural Language Understanding

Improving Generalization of Pretrained Language Models

Backpropagation-free training of deep physical neural networks

Hearing functional harmony in jazz: A perceptual study on music-theoretical accounts of extended tonality