Related papers: MusicLIME: Explainable Multimodal Music Understand…

Music emotion recognition is an important task in MIR (Music Information Retrieval) research. Owing to factors like the subjective nature of the task and the variation of emotional cues between musical genres, there are still significant…

Deep neural networks (DNNs) are successfully applied in a wide variety of music information retrieval (MIR) tasks. Such models are usually considered "black boxes", meaning that their predictions are not interpretable. Prior work on…

Deep neural networks (DNNs) are successfully applied in a wide variety of music information retrieval (MIR) tasks but their predictions are usually not interpretable. We propose audioLIME, a method based on Local Interpretable…

Recent advancements in music large language models (LLMs) have significantly improved music understanding tasks, which involve the model's ability to analyze and interpret various musical elements. These improvements primarily focused on…

Recent advances in multimodal large language models (MLLM) for audio music have demonstrated strong capabilities in music understanding, yet symbolic music, a fundamental representation of musical structure, remains unexplored. In this…

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 similarity is an essential aspect of music retrieval, recommendation systems, and music analysis. Moreover, similarity is of vital interest for music experts, as it allows studying analogies and influences among composers and…

Local Interpretable Model-Agnostic Explanations (LIME) is a popular method to perform interpretability of any kind of Machine Learning (ML) model. It explains one ML prediction at a time, by learning a simple linear model around the…

Music is essential in daily life, fulfilling emotional and entertainment needs, and connecting us personally, socially, and culturally. A better understanding of music can enhance our emotions, cognitive skills, and cultural connections.…

Multimodal models that jointly process audio and language hold great promise in audio understanding and are increasingly being adopted in the music domain. By allowing users to query via text and obtain information about a given audio…

Music auto-tagging is essential for organizing and discovering music in extensive digital libraries. While foundation models achieve exceptional performance in this domain, their outputs often lack interpretability, limiting trust and…

Music performances are representative scenarios for audio-visual modeling. Unlike common scenarios with sparse audio, music performances continuously involve dense audio signals throughout. While existing multimodal learning methods on the…

Ensuring transparency in machine learning decisions is critically important, especially in sensitive sectors such as healthcare, finance, and justice. Despite this, some popular explainable algorithms, such as Local Interpretable…

The ability for a human to understand an Artificial Intelligence (AI) model's decision-making process is critical in enabling stakeholders to visualize model behavior, perform model debugging, promote trust in AI models, and assist in…

Multimodal Large Language Models (LLMs) claim "musical understanding" via evaluations that conflate listening with score reading. We benchmark three SOTA LLMs (Gemini 2.5 Pro, Gemini 2.5 Flash, and Qwen2.5-Omni) across three core music…

Despite recent advances in multimodal large language models (MLLMs), their ability to understand and interact with music remains limited. Music understanding requires grounded reasoning over symbolic scores and expressive performance audio,…

Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user…

Local explanation methods such as LIME have become popular in MIR as tools for generating post-hoc, model-agnostic explanations of a model's classification decisions. The basic idea is to identify a small set of human-understandable…

This study explores the development of an explainable music recommendation system with enhanced user control. Leveraging a hybrid of collaborative filtering and content-based filtering, we address the challenges of opaque recommendation…

Most state-of-the-art machine learning algorithms induce black-box models, preventing their application in many sensitive domains. Hence, many methodologies for explaining machine learning models have been proposed to address this problem.…