Related papers: MusER: Musical Element-Based Regularization for Ge…
Recent years have seen remarkable progress in speech emotion recognition (SER), thanks to advances in deep learning techniques. However, the limited availability of labeled data remains a significant challenge in the field. Self-supervised…
Conventional Multi-modal multi-label emotion recognition (MMER) assumes complete access to visual, textual, and acoustic modalities. However, real-world multi-party settings often violate this assumption, as non-speakers frequently lack…
The representation of basic elements of music in terms of discrete audio signals is often used in software for musical creation and design. Nevertheless, there is no unified approach that relates these elements to the discrete samples of…
In this paper, we propose a lightweight music-generating model based on variational autoencoder (VAE) with structured attention. Generating music is different from generating text because the melodies with chords give listeners…
Generative models have thrived in computer vision, enabling unprecedented image processes. Yet the results in audio remain less advanced. Our project targets real-time sound synthesis from a reduced set of high-level parameters, including…
Timbre spaces have been used in music perception to study the perceptual relationships between instruments based on dissimilarity ratings. However, these spaces do not generalize to novel examples and do not provide an invertible mapping,…
Large language models are routinely deployed on text that varies widely in emotional tone, yet their reasoning behavior is typically evaluated without accounting for emotion as a source of representational variation. Prior work has largely…
Generating music from images can enhance various applications, including background music for photo slideshows, social media experiences, and video creation. This paper presents an emotion-guided image-to-music generation framework that…
Interpretability is essential for deploying deep learning models in symbolic music analysis, yet most research emphasizes model performance over explanation. To address this, we introduce MUSE-Explainer, a new method that helps reveal how…
Music representation learning is notoriously difficult for its complex human-related concepts contained in the sequence of numerical signals. To excavate better MUsic SEquence Representation from labeled audio, we propose a novel…
Recent approaches in music generation rely on disentangled representations, often labeled as structure and timbre or local and global, to enable controllable synthesis. Yet the underlying properties of these embeddings remain underexplored.…
Multimodal Large Language Models (MLLMs) excel in Open-Vocabulary (OV) emotion recognition but often neglect fine-grained acoustic modeling. Existing methods typically use global audio encoders, failing to capture subtle, local temporal…
This paper presents an architecture for generating music for video games based on the Transformer deep learning model. Our motivation is to be able to customize the generation according to the taste of the player, who can select a corpus of…
Autoencoders and their variations provide unsupervised models for learning low-dimensional representations for downstream tasks. Without proper regularization, autoencoder models are susceptible to the overfitting problem and the so-called…
Symbolic melodies generation is one of the essential tasks for automatic music generation. Recently, models based on neural networks have had a significant influence on generating symbolic melodies. However, the musical context structure is…
Recent advances in music generation produce impressive samples, however, practical creation still lacks two key capabilities: composer-style structural editing and minute-scale coherence. We present MusicWeaver, a framework for generating…
Symbolic music generation has made significant progress, yet achieving fine-grained and flexible control over composer style remains challenging. Existing training-based methods for composer style conditioning depend on large labeled…
Estimating direct and indirect causal effects from observational data is crucial to understanding the causal mechanisms and predicting the behaviour under different interventions. Causal mediation analysis is a method that is often used to…
Controllable timbre synthesis has been a subject of research for several decades, and deep neural networks have been the most successful in this area. Deep generative models such as Variational Autoencoders (VAEs) have the ability to…
Since most of music has repetitive structures from motifs to phrases, repeating musical ideas can be a basic operation for music composition. The basic block that we focus on is conceptualized as loops which are essential ingredients of…