MuRS: 3rd Music Recommender Systems Workshop
Revolutionizing Music Discovery in the Age of AI-Generated Content
Andres Ferraro (Pandora/SiriusXM), Lorenzo Porcaro (Sapienza University of Rome), Christine Bauer (Paris Lodron University Salzburg)
Music recommendation, a cornerstone of the RecSys community, faces unprecedented challenges with the rise of AI-generated music. This 3rd MuRS workshop addresses critical questions concerning discoverability, authenticity, and the curational role of recommender systems in a rapidly evolving streaming ecosystem. Our goal is to foster transparent, fair, and accountable recommendation frameworks for all stakeholders.
Key Impact Areas & Strategic Focus
The 3rd MuRS workshop highlights pivotal shifts and emerging priorities in music recommendation, driven by the increasing influence of AI and the need for interdisciplinary collaboration.
0
Workshop Editions
0
Focus on AI-Generated Content
0
Stakeholder Alignment Goal
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
Fundamentals
Applications
Societal Aspects
Exploring Core Principles
This section delves into the foundational research areas that underpin music recommender systems, highlighting ongoing advancements and critical challenges:
- Sequential music recommendation: Enhancing recommendations for continuous listening experiences.
- Bandits and reinforcement learning: Applying adaptive strategies for dynamic recommendation.
- Large language models: Utilizing advanced NLP for music understanding and generation.
- Multi-stakeholder and multi-objective: Balancing interests of users, artists, and platforms.
- Music representation learning: Developing effective methods to represent music data.
- Music content understanding: Extracting meaningful features from audio and metadata.
- Mitigating biases: Addressing cold-start and popularity bias for fair exposure.
- Hybrid methods: Combining content-based and collaborative filtering with multi-modal information.
- Listener modeling: Understanding user taste, intent (session-level, long-term), and context.
- Fairness, transparency, interpretability, & explainability: Building trustworthy systems.
- Online and offline evaluation: Rigorous assessment of system performance.
- Engineering at scale: Addressing technical challenges for large-scale deployments.
- User studies: Empirical research on music consumption and user experience.
Practical System Implementations
This tab outlines various practical applications and specialized areas where music recommendation algorithms are deployed to enhance user experience and industry processes:
- Playlist generation and continuation: Automated creation and extension of music playlists.
- Algorithmic radio programming: Curating continuous, personalized radio-like streams.
- Visual recommendations: Integrating visual cues for homepage personalization.
- Music discovery: Helping users find new and relevant music.
- Music search and browsing: Improving retrieval and exploration interfaces.
- Conversational interaction: Enabling natural language interaction with systems.
- Virtual reality and listening experiences: Innovations in immersive music consumption.
- Social media: Music recommendation within social platforms.
- Live music industry: Supporting discovery for concerts and events.
- Record labels: Tools for artist promotion and market analysis.
- Music creation and generation: Recommender systems aiding in the creative process for artists.
Broader Societal Implications
This section discusses the wider impact of music recommender systems on culture, society, and ethical considerations:
- Cross-cultural music recommendation: Bridging cultural divides in music discovery.
- Local music recommendation: Promoting regional and niche artists.
- Socially-aware systems: Designing recommendations that consider social context.
- Impact studies: Research on the societal effects of algorithmic music recommendation.
- Ethics: Addressing moral principles and values in system design.
AI-Generated Music
Driving the 3rd MuRS Workshop Focus
This third edition of MuRS focuses on the growing impact of generative content on music recommendation. The rapid influx of AI-generated music reshapes the streaming ecosystem, raising critical questions about discoverability, authenticity, and the curational role of recommender systems.
MuRS 2025 Paper Flow
Paper Submission (Regular/Position)
→
Single-Anonymized Peer Review
→
Selection by Program Committee
→
Oral Presentations & Discussion
→
Proceedings Publication (ceur-ws.org)
| Feature | RecSys Community Focus | MIR Community Focus |
|---|---|---|
| Primary Objective | Building effective recommendation algorithms and user experiences. | Analyzing audio and music content for features and understanding. |
| Content Understanding | Historically placed less emphasis on deep content understanding. | Core focus on audio and content analysis, feature extraction. |
| Recommendation Engagement | Strong engagement in designing and evaluating recommendation. | Limited direct engagement in recommendation system design. |
| Typical Output | Personalized lists, playlists, next-track suggestions. | Tags, genres, mood detection, similarity measures from audio. |
Evolution of the MuRS Workshop
Context: The Music Recommender Systems (MuRS) workshop was initially launched to bridge a critical gap between the Recommender Systems (RecSys) and Music Information Retrieval (MIR) communities, which historically operated in silos despite their shared domain.
Challenge: To foster interdisciplinary collaboration and address the complex, evolving challenges in music recommendation that require insights from both algorithm design and deep content analysis.
Solution & Outcome: The first two editions of MuRS, held at RecSys 2023 and 2024, successfully attracted balanced submissions from both academia and industry. These workshops provided dedicated forums to explore diverse topics, including biases, algorithmic improvements, artist-focused recommendations, music discoverability, multimodal embeddings, and emotion prediction. This continuous engagement demonstrates MuRS's role in advancing the field through integrated research and discussion.
Estimate Your Enterprise AI ROI
Calculate the potential time and cost savings by implementing AI-driven solutions in your operations, inspired by the efficiencies discussed in this analysis.
Estimated Annual Savings
$0
Annual Hours Reclaimed
0
MuRS 2025 Workshop Roadmap
A phased approach to the 3rd Music Recommender Systems Workshop, from content submission to post-event publication, designed for maximum engagement and knowledge dissemination.
Phase 1: Call for Contributions
We solicit regular papers (max. 8 pages) and position papers (max. 4 pages), welcoming both work in progress and already published results from academia and industry. Emphasizing relevance, quality, novelty, clarity, and discussion potential.
Phase 2: Peer Review and Selection
Submissions undergo single-anonymized peer review by at least two Program Committee (PC) members. Selection is based on relevance to the workshop's central theme of AI-generated music, overall quality, and potential for stimulating discussion.
Phase 3: Workshop Execution
The half-day hybrid workshop will feature a keynote address by Cheng-Zhi Anna Huang (MIT) on "In Search of Human-AI Resonance," followed by short oral presentations of accepted papers and brief discussions, fostering interdisciplinary collaboration.
Phase 4: Post-Workshop Publication
Accepted papers will be included in the official proceedings, submitted to ceur-ws.org for online publication, ensuring broad accessibility and impact of the research presented at MuRS 2025.
Ready to Shape the Future of Music AI?
The rapid evolution of AI in music recommendation demands proactive strategy. Connect with our experts to navigate these challenges and unlock new opportunities for your enterprise.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat