Sergio Oramas
Research Subjects
Sergio Oramas has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Bruno Sguerra
Deezer Research, Paris, France
3 shared publications - Seungheon Doh
Sony Group Corporation, Tokyo, Japan
3 shared publications - Xavier Serra
Universitat Pompeu Fabra, Barcelona, Spain
3 shared publications - Abhinav Bohra
Amazon, Seattle, USA
2 shared publications - Claudio Pomo
Politecnico di Bari, Bari, Italy
2 shared publications - Francesco Barbieri
TALN Group, Universitat Pompeu Fabra, Barcelona
2 shared publications
Latest Publications
- Open Access
- 2 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Overview and Analysis of the RecSys Challenge 2026: Conversational Music Recommendation
The RecSys Challenge 2026 studies conversational music recommendation as a joint item recommendation and response generation problem: given a multi-turn dialogue, systems must retrieve relevant tracks from a large catalog and produce a grounded natural-language response. This paper presents the challenge task, dataset, evaluation protocol, and official results. Beyond the leaderboard, we analyze the 16 accepted systems through a common retrieve–rerank–generate framework and examine how recommendation performance varies across users, requests, and dialogue contexts. Strong systems commonly combine heterogeneous candidate sources and preserve source-specific evidence for learned reranking. Across the system papers and our organizer-side analysis, robust design also means 1) grounding cold-start retrieval in multi-turn conversation and item signals, 2) using intent detectors, and 3) modeling the full multi-turn context rather than the current query alone. We further identify limitations of the benchmark and evaluation protocol, including single-ground-truth relevance and teacher-forced evaluation of synthetic dialogues. Together, these findings provide practical guidance for future conversational recommender systems and shared evaluation efforts.
- 2 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessOverview and Analysis of the RecSys Challenge 2026: Conversational Music Recommendation
The RecSys Challenge 2026 studies conversational music recommendation as a joint item recommendation and response generation problem: given a multi-turn dialogue, systems must retrieve relevant tracks from a large catalog and produce a grounded natural-language response. This paper presents the challenge task, dataset, evaluation protocol, and official results. Beyond the leaderboard, we analyze the 16 accepted systems through a common retrieve–rerank–generate framework and examine how recommendation performance varies across users, requests, and dialogue contexts. Strong systems commonly combine heterogeneous candidate sources and preserve source-specific evidence for learned reranking. Across the system papers and our organizer-side analysis, robust design also means 1) grounding cold-start retrieval in multi-turn conversation and item signals, 2) using intent detectors, and 3) modeling the full multi-turn context rather than the current query alone. We further identify limitations of the benchmark and evaluation protocol, including single-ground-truth relevance and teacher-forced evaluation of synthetic dialogues. Together, these findings provide practical guidance for future conversational recommender systems and shared evaluation efforts.
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 708-714
LLM-as-a-Judge for Evaluating System Responses in Conversational Music Recommendation
Conversational Recommendation Systems (CRS) aim to achieve two primary objectives: recommending relevant items and generating natural language responses. While recommendation accuracy is effectively measured by established ranking metrics, the evaluation of response generation poses a more fundamental challenge. Although human evaluation remains the gold standard, its cost and scalability constraints have motivated the adoption of LLM-as-a-judge as a promising proxy, whose alignment with human judgment in the context of CRS remains an open question. In this paper, we present the first user study to empirically assess the reliability of LLM-as-a-judge for evaluating CRS responses. We sample 20 multi-turn music recommendation sessions and generate candidate system responses using four instruction-tuned LLMs, inducing variance in response quality across model scales. We collect n = 400 ratings from 20 domain-expert annotators, who evaluate each response across two dimensions: Personalization Quality and Explanation Quality. Through bootstrapped correlation analysis, we find that LLM-based judges exhibit moderate positive alignment with human assessments and outperform all reference-based baselines. Furthermore, we analyze how judge performance varies according to model scale and conditioning information, providing practical guidance for deploying LLM-as-a-judge. 1
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 708-714
Open AccessLLM-as-a-Judge for Evaluating System Responses in Conversational Music Recommendation
Conversational Recommendation Systems (CRS) aim to achieve two primary objectives: recommending relevant items and generating natural language responses. While recommendation accuracy is effectively measured by established ranking metrics, the evaluation of response generation poses a more fundamental challenge. Although human evaluation remains the gold standard, its cost and scalability constraints have motivated the adoption of LLM-as-a-judge as a promising proxy, whose alignment with human judgment in the context of CRS remains an open question. In this paper, we present the first user study to empirically assess the reliability of LLM-as-a-judge for evaluating CRS responses. We sample 20 multi-turn music recommendation sessions and generate candidate system responses using four instruction-tuned LLMs, inducing variance in response quality across model scales. We collect n = 400 ratings from 20 domain-expert annotators, who evaluate each response across two dimensions: Personalization Quality and Explanation Quality. Through bootstrapped correlation analysis, we find that LLM-based judges exhibit moderate positive alignment with human assessments and outperform all reference-based baselines. Furthermore, we analyze how judge performance varies according to model scale and conditioning information, providing practical guidance for deploying LLM-as-a-judge. 1
- Top Cited PapersOpen Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1861-1863
RecSys Challenge 2026: Conversational Music Recommendation
The RecSys Challenge 2026 focuses on the evolving landscape of music discovery, where static recommendation lists are being replaced by dynamic, conversational interactions. As users increasingly interact with AI through natural language, there is a critical need for systems that can seamlessly integrate Natural Language Understanding (NLU) with high-precision Recommender Systems (RecSys). The challenge pushes the boundaries of how AI understands nuanced user preferences, explores musical tastes through dialogue, and provides contextually relevant track recommendations. The participants are asked to tackle the complexities of multi-turn preference elicitation, using the TalkPlayData-Challenge dataset, a large-scale conversation resource generated through an advanced agentic pipeline. The dataset features LLM-generated multi-turn dialogues paired with music metadata and user-item interaction data derived from publicly available research datasets. This challenge bridges the NLP and RecSys communities, driving innovation in interactive, personalized music information retrieval.
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1861-1863
Top Cited PapersOpen AccessRecSys Challenge 2026: Conversational Music Recommendation
The RecSys Challenge 2026 focuses on the evolving landscape of music discovery, where static recommendation lists are being replaced by dynamic, conversational interactions. As users increasingly interact with AI through natural language, there is a critical need for systems that can seamlessly integrate Natural Language Understanding (NLU) with high-precision Recommender Systems (RecSys). The challenge pushes the boundaries of how AI understands nuanced user preferences, explores musical tastes through dialogue, and provides contextually relevant track recommendations. The participants are asked to tackle the complexities of multi-turn preference elicitation, using the TalkPlayData-Challenge dataset, a large-scale conversation resource generated through an advanced agentic pipeline. The dataset features LLM-generated multi-turn dialogues paired with music metadata and user-item interaction data derived from publicly available research datasets. This challenge bridges the NLP and RecSys communities, driving innovation in interactive, personalized music information retrieval.
- Open Access
- 27 October 2022
- Published by Ubiquity Press, Ltd. in Transactions of the International Society for Music Information Retrieval
- Vol. 5 (1) , 129-140
Artist Similarity for Everyone: A Graph Neural Network Approach
- 27 October 2022
- Published by Ubiquity Press, Ltd. in Transactions of the International Society for Music Information Retrieval
- Vol. 5 (1) , 129-140
Open AccessArtist Similarity for Everyone: A Graph Neural Network Approach
- Top Cited PapersOpen Access
- 4 September 2018
- Published by Ubiquity Press, Ltd. in Transactions of the International Society for Music Information Retrieval
- Vol. 1 (1) , 4-21
Multimodal Deep Learning for Music Genre Classification
Music genre labels are useful to organize songs, albums, and artists into broader groups that share similar musical characteristics. In this work, an approach to learn and combine multimodal data representations for music genre classification is proposed. Intermediate representations of deep neural networks are learned from audio tracks, text reviews, and cover art images, and further combined for classification. Experiments on single and multi-label genre classification are then carried out, evaluating the effect of the different learned representations and their combinations. Results on both experiments show how the aggregation of learned representations from different modalities improves the accuracy of the classification, suggesting that different modalities embed complementary information. In addition, the learning of a multimodal feature space increases the performance of pure audio representations, which may be specially relevant when the other modalities are available for training, but not at prediction time. Moreover, a proposed approach for dimensionality reduction of target labels yields major improvements in multi-label classification not only in terms of accuracy, but also in terms of the diversity of the predicted genres, which implies a more fine-grained categorization. Finally, a qualitative analysis of the results sheds some light on the behavior of the different modalities on the classification task.
- 4 September 2018
- Published by Ubiquity Press, Ltd. in Transactions of the International Society for Music Information Retrieval
- Vol. 1 (1) , 4-21
Top Cited PapersOpen AccessMultimodal Deep Learning for Music Genre Classification
Music genre labels are useful to organize songs, albums, and artists into broader groups that share similar musical characteristics. In this work, an approach to learn and combine multimodal data representations for music genre classification is proposed. Intermediate representations of deep neural networks are learned from audio tracks, text reviews, and cover art images, and further combined for classification. Experiments on single and multi-label genre classification are then carried out, evaluating the effect of the different learned representations and their combinations. Results on both experiments show how the aggregation of learned representations from different modalities improves the accuracy of the classification, suggesting that different modalities embed complementary information. In addition, the learning of a multimodal feature space increases the performance of pure audio representations, which may be specially relevant when the other modalities are available for training, but not at prediction time. Moreover, a proposed approach for dimensionality reduction of target labels yields major improvements in multi-label classification not only in terms of accuracy, but also in terms of the diversity of the predicted genres, which implies a more fine-grained categorization. Finally, a qualitative analysis of the results sheds some light on the behavior of the different modalities on the classification task.
- 5 July 2018
- Published by Taylor & Francis in Journal of New Music Research
- Vol. 47 (4) , 365-382
Natural language processing for music knowledge discovery
Today, a massive amount of musical knowledge is stored in written form, with testimonies dated as far back as several centuries ago. In this work, we present different Natural Language Processing (NLP) approaches to harness the potential of these text collections for automatic music knowledge discovery, covering different phases in a prototypical NLP pipeline, namely corpus compilation, text-mining, information extraction, knowledge graph generation, and sentiment analysis. Each of these approaches is presented alongside different use cases (i.e. flamenco, Renaissance and popular music) where large collections of documents are processed, and conclusions stemming from data-driven analyses are presented and discussed.
- 5 July 2018
- Published by Taylor & Francis in Journal of New Music Research
- Vol. 47 (4) , 365-382
Natural language processing for music knowledge discovery
Today, a massive amount of musical knowledge is stored in written form, with testimonies dated as far back as several centuries ago. In this work, we present different Natural Language Processing (NLP) approaches to harness the potential of these text collections for automatic music knowledge discovery, covering different phases in a prototypical NLP pipeline, namely corpus compilation, text-mining, information extraction, knowledge graph generation, and sentiment analysis. Each of these approaches is presented alongside different use cases (i.e. flamenco, Renaissance and popular music) where large collections of documents are processed, and conclusions stemming from data-driven analyses are presented and discussed.
- Open Access
Multi-label Music Genre Classification from Audio, Text, and Images Using Deep Features
Music genres allow to categorize musical items that share common characteristics. Although these categories are not mutually exclusive, most related research is traditionally focused on classifying tracks into a single class. Furthermore, these categories (e.g., Pop, Rock) tend to be too broad for certain applications. In this work we aim to expand this task by categorizing musical items into multiple and fine-grained labels, using three different data modalities: audio, text, and images. To this end we present MuMu, a new dataset of more than 31k albums classified into 250 genre classes. For every album we have collected the cover image, text reviews, and audio tracks. Additionally, we propose an approach for multi-label genre classification based on the combination of feature embeddings learned with state-of-the-art deep learning methodologies. Experiments show major differences between modalities, which not only introduce new baselines for multi-label genre classification, but also suggest that combining them yields improved results.
Open AccessMulti-label Music Genre Classification from Audio, Text, and Images Using Deep Features
Music genres allow to categorize musical items that share common characteristics. Although these categories are not mutually exclusive, most related research is traditionally focused on classifying tracks into a single class. Furthermore, these categories (e.g., Pop, Rock) tend to be too broad for certain applications. In this work we aim to expand this task by categorizing musical items into multiple and fine-grained labels, using three different data modalities: audio, text, and images. To this end we present MuMu, a new dataset of more than 31k albums classified into 250 genre classes. For every album we have collected the cover image, text reviews, and audio tracks. Additionally, we propose an approach for multi-label genre classification based on the combination of feature embeddings learned with state-of-the-art deep learning methodologies. Experiments show major differences between modalities, which not only introduce new baselines for multi-label genre classification, but also suggest that combining them yields improved results.
- 1 November 2016
- Published by Elsevier in Data & Knowledge Engineering
- Vol. 106, 70-83
Information extraction for knowledge base construction in the music domain
- 1 November 2016
- Published by Elsevier in Data & Knowledge Engineering
- Vol. 106, 70-83
Information extraction for knowledge base construction in the music domain
- 4 June 2015
- Published by Springer Nature
- p. 369-382
Extracting Relations from Unstructured Text Sources for Music Recommendation
- 4 June 2015
- Published by Springer Nature
- p. 369-382
Extracting Relations from Unstructured Text Sources for Music Recommendation