1 citations · 1 across the 11 of their papers we have counts for
16 papers
Distilling Diffusion Score Discrepancy for Efficient Training Data Attribution
Shixuan Liu, Joan Serrà, Kin Wai Cheuk +6
Training data attribution for diffusion models aims to identify the training samples that influence a generated instance, but existing methods either require costly per-sample grad…
Training Music Sample Identification Models on Real Sample Pairs
R. Oguz Araz, Joan Serrà, Xavier Lizarraga-Seijas +4
Sample identification (SI) is the task of matching pairs of tracks, where one track is created by musically transforming an element of the other. In the absence of sample annotatio…
On the Human and Computer Alignment of Attribute-Based Music Matches
Roser Batlle-Roca, Woosung Choi, Joan Serrà +5
Recent advances in generative AI are raising ethical concerns regarding the originality of generated content and the potential replication of training data, with further implicatio…
Unified Music Identification for Tracks and Versions
R. Oguz Araz, Joan Serrà, Yuki Mitsufuji +2
Given a music database, track identification (TI) retrieves the exact track matching an audio excerpt, whereas version identification (VI) retrieves its musical versions. Tradition…
Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew
Joan Serrà, Dipam Goswami, Fabio Morreale +2
Training data attribution (TDA) should enable generative model interpretability and foster a variety of related downstream tasks. Nonetheless, current TDA approaches lack reliabili…
Woosh: A Sound Effects Foundation Model
Gaëtan Hadjeres, Marc Ferras, Khaled Koutini +7
The audio research community depends on open generative models as foundational tools for building novel approaches and establishing baselines. In this report, we present Woosh, Son…
Emergent, not Immanent: A Baradian Reading of Explainable AI
Fabio Morreale, Joan Serrà, Yuki Mitsufuji
Explainable AI (XAI) is frequently positioned as a technical problem of revealing the inner workings of an AI model. This position is affected by unexamined onto-epistemological as…
Automatic Music Mixing using a Generative Model of Effect Embeddings
Eloi Moliner, Marco A. Martínez-Ramírez, Junghyun Koo +5
Music mixing involves combining individual tracks into a cohesive mixture, a task characterized by subjectivity where multiple valid solutions exist for the same input. Existing au…
Automatic Music Sample Identification with Multi-Track Contrastive Learning
Alain Riou, Joan Serrà, Yuki Mitsufuji
Sampling, the technique of reusing pieces of existing audio tracks to create new music content, is a very common practice in modern music production. In this paper, we tackle the c…
Towards Blind Data Cleaning: A Case Study in Music Source Separation
Azalea Gui, Woosung Choi, Junghyun Koo +5
The performance of deep learning models for music source separation heavily depends on training data quality. However, datasets are often corrupted by difficult-to-detect artifacts…
Attribution-by-design: Ensuring Inference-Time Provenance in Generative Music Systems
Fabio Morreale, Wiebke Hutiri, Joan Serrà +2
The rise of AI-generated music is diluting royalty pools and revealing structural flaws in existing remuneration frameworks, challenging the well-established artist compensation sy…
Leveraging Whisper Embeddings for Audio-based Lyrics Matching
Eleonora Mancini, Joan Serrà, Paolo Torroni +1
Audio-based lyrics matching can be an appealing alternative to other content-based retrieval approaches, but existing methods often suffer from limited reproducibility and inconsis…
Enhancing Neural Audio Fingerprint Robustness to Audio Degradation for Music Identification
R. Oguz Araz, Guillem Cortès-Sebastià, Emilio Molina +4
Audio fingerprinting (AFP) allows the identification of unknown audio content by extracting compact representations, termed audio fingerprints, that are designed to remain robust a…
Large-Scale Training Data Attribution for Music Generative Models via Unlearning
Woosung Choi, Junghyun Koo, Kin Wai Cheuk +7
This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specifi…
A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?
Yigitcan Özer, Woosung Choi, Joan Serrà +3
We introduce the Robust Audio Watermarking Benchmark (RAW-Bench), a benchmark for evaluating deep learning-based audio watermarking methods with standardized and systematic compari…
Supervised contrastive learning from weakly-labeled audio segments for musical version matching
Joan Serrà, R. Oguz Araz, Dmitry Bogdanov +1
Detecting musical versions (different renditions of the same piece) is a challenging task with important applications. Because of the ground truth nature, existing approaches match…