The Deep Learning Revolution in MIR: The Pros and Cons, the Needs and the Challenges

Peeters, Geoffroy

doi:10.1007/978-3-030-70210-6_1

Cited by 3 publications

(1 citation statement)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yet, in spite of these advances, several challenges and open questions remain. Deep learning methods are known to be highly data-sensitive [27]. The knowledge they acquire is directly linked both to the quality of the annotated data and the scope of musical material to which they have been exposed.…”

Section: Introductionmentioning

confidence: 99%

User-Driven Fine-Tuning for Beat Tracking

Pinto

Böck²,

Cardoso

et al. 2021

Electronics

View full text Add to dashboard Cite

The extraction of the beat from musical audio signals represents a foundational task in the field of music information retrieval. While great advances in performance have been achieved due the use of deep neural networks, significant shortcomings still remain. In particular, performance is generally much lower on musical content that differs from that which is contained in existing annotated datasets used for neural network training, as well as in the presence of challenging musical conditions such as rubato. In this paper, we positioned our approach to beat tracking from a real-world perspective where an end-user targets very high accuracy on specific music pieces and for which the current state of the art is not effective. To this end, we explored the use of targeted fine-tuning of a state-of-the-art deep neural network based on a very limited temporal region of annotated beat locations. We demonstrated the success of our approach via improved performance across existing annotated datasets and a new annotation-correction approach for evaluation. Furthermore, we highlighted the ability of content-specific fine-tuning to learn both what is and what is not the beat in challenging musical conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

User-Driven Fine-Tuning for Beat Tracking

Pinto

Böck²,

Cardoso

et al. 2021

Electronics

View full text Add to dashboard Cite

show abstract

Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio

Alonso-Jiménez,

Pepino,

Batlle-Roca

et al. 2024

2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)

View full text Add to dashboard Cite

Interpretability of Methods for Switch Point Detection in Electronic Dance Music

Zehren,

Alunno,

Bientinesi

2024

Signals

View full text Add to dashboard Cite

Switch points are a specific kind of cue point that DJs carefully look for when mixing music tracks. As the name says, a switch point is the point in time where the current track in a DJ mix is replaced by the upcoming track. Being able to identify these positions is a first step toward the interpretation and the emulation of DJ mixes. With the aim of automatically detecting switch points, we evaluate one experience-driven and several statistics-driven methods. By comparing the decision process of each method, contrasted by their performance, we deduce the characteristics linked to switch points. Specifically, we identify the most impactful features for their detection, namely, the novelty in the signal energy, the timbre, the number of drum onsets, and the harmony. Furthermore, we expose multiple interactions among these features.

show abstract

The Deep Learning Revolution in MIR: The Pros and Cons, the Needs and the Challenges

Cited by 3 publications

References 66 publications

User-Driven Fine-Tuning for Beat Tracking

User-Driven Fine-Tuning for Beat Tracking

Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio

Interpretability of Methods for Switch Point Detection in Electronic Dance Music

Contact Info

Product

Resources

About