Federico Simonetta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Federico Simonetta has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Stavros Ntalampiras
University of Milan
7 shared publications - Sachin Sharma
GSSI – Gran Sasso Science Institute
3 shared publications - Michele Flammini
Gran Sasso Science Institute, L’Aquila, Italy
2 shared publications Adriano Baratè
University of Milan
1 shared publicationAlessandro Maria Poirè
University of Milano
1 shared publication- Ali Tabaraei
University of Milan
1 shared publication
Latest Publications
- 28 August 2026
- Published by Springer Nature
- p. 215-228
TrOCR for Medieval HTR: A Systematic Ablation Study with Cross-Dataset Validation
- 28 August 2026
- Published by Springer Nature
- p. 215-228
TrOCR for Medieval HTR: A Systematic Ablation Study with Cross-Dataset Validation
- Open Access
- 8 July 2026
- Published by Springer Nature in Research Square
TrOCR for Medieval HTR: A Systematic Ablation Study with Cross-Dataset Validation
Fine-tuning transformer-based handwritten text recognition (HTR) models on medieval manuscripts is challenging because these models are pre-trained on modern text and must adapt to a very different visual domain. This paper studies how three controllable finetuning choices (contrast normalization, data augmentation, and layer freezing) affect recognition accuracy when adapting TrOCR to small historical datasets. We run controlled experiments on a 13th-century Italian manuscript (I-CT 91 “Cortonese”) and replicate the same experimental grid on the public READ-16 benchmark as robustness evidence. On Cortonese, our best configuration achieves 8.03% character error rate (CER). Statistical comparisons across 13 configurations show that freezing up to three encoder layers or six decoder layers does not significantly harm accuracy, while deeper freezing becomes progressively detrimental. Removing contrast normalization (CLAHE) yields 7.84% CER, comparable to a domain-specialized baseline, suggesting strong optimization can reduce reliance on image preprocessing. Cross-dataset validation on READ-16 shows that decoder freezing thresholds transfer more robustly than encoder thresholds, and combined freezing strategies require dataset-specific re-validation. Finally, we use Grad-CAM gradient attributions and decoder cross-attention maps to diagnose error patterns and failure modes revealed by the ablations. Source code is available at https://github.com/LaudareProject/TrOCR-analysis
- 8 July 2026
- Published by Springer Nature in Research Square
Open AccessTrOCR for Medieval HTR: A Systematic Ablation Study with Cross-Dataset Validation
Fine-tuning transformer-based handwritten text recognition (HTR) models on medieval manuscripts is challenging because these models are pre-trained on modern text and must adapt to a very different visual domain. This paper studies how three controllable finetuning choices (contrast normalization, data augmentation, and layer freezing) affect recognition accuracy when adapting TrOCR to small historical datasets. We run controlled experiments on a 13th-century Italian manuscript (I-CT 91 “Cortonese”) and replicate the same experimental grid on the public READ-16 benchmark as robustness evidence. On Cortonese, our best configuration achieves 8.03% character error rate (CER). Statistical comparisons across 13 configurations show that freezing up to three encoder layers or six decoder layers does not significantly harm accuracy, while deeper freezing becomes progressively detrimental. Removing contrast normalization (CLAHE) yields 7.84% CER, comparable to a domain-specialized baseline, suggesting strong optimization can reduce reliance on image preprocessing. Cross-dataset validation on READ-16 shows that decoder freezing thresholds transfer more robustly than encoder thresholds, and combined freezing strategies require dataset-specific re-validation. Finally, we use Grad-CAM gradient attributions and decoder cross-attention maps to diagnose error patterns and failure modes revealed by the ablations. Source code is available at https://github.com/LaudareProject/TrOCR-analysis
- Open Access
- 25 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 28-35
Drafting the Landscape of Computational Musicology Tools: a Survey-Based Approach
- 25 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 28-35
Open AccessDrafting the Landscape of Computational Musicology Tools: a Survey-Based Approach
- Open Access
- 7 February 2025
- Published by Ubiquity Press, Ltd. in Transactions of the International Society for Music Information Retrieval
- Vol. 8 (1)
Style-Based Composer Identification and Attribution of Symbolic Music Scores: A Systematic Survey
This paper presents the first comprehensive systematic review of literature on style-based composer identification and authorship attribution in symbolic music scores. Addressing the critical need for improved reliability and reproducibility in this field, the review rigorously analyzes 58 peer-reviewed papers published across various historical periods, with the search adapted to accommodate evolving terminology. The analysis critically assesses prevailing repertoires, computational approaches, and evaluation methodologies, highlighting significant challenges. It reveals that a substantial portion of existing research suffers from inadequate validation protocols and an over-reliance on simple accuracy metrics for often-imbalanced datasets, which can undermine the credibility of attribution claims. The crucial role of robust metrics like Balanced Accuracy and rigorous cross-validation in ensuring trustworthy results is emphasized. The survey also details diverse feature representations and the evolution of machine learning models employed. Notable real-world authorship attribution cases, such as those involving works attributed to Bach, Josquin des Prez, and Lennon–McCartney, are specifically discussed, illustrating the opportunities and pitfalls of applying computational techniques to resolve disputed musical provenance. Based on these insights, a set of actionable guidelines for future research are proposed. These recommendations are designed to significantly enhance the reliability, reproducibility, and musicological validity of composer identification and authorship attribution studies, fostering more robust and interpretable computational stylistic analysis.
- 7 February 2025
- Published by Ubiquity Press, Ltd. in Transactions of the International Society for Music Information Retrieval
- Vol. 8 (1)
Open AccessStyle-Based Composer Identification and Attribution of Symbolic Music Scores: A Systematic Survey
This paper presents the first comprehensive systematic review of literature on style-based composer identification and authorship attribution in symbolic music scores. Addressing the critical need for improved reliability and reproducibility in this field, the review rigorously analyzes 58 peer-reviewed papers published across various historical periods, with the search adapted to accommodate evolving terminology. The analysis critically assesses prevailing repertoires, computational approaches, and evaluation methodologies, highlighting significant challenges. It reveals that a substantial portion of existing research suffers from inadequate validation protocols and an over-reliance on simple accuracy metrics for often-imbalanced datasets, which can undermine the credibility of attribution claims. The crucial role of robust metrics like Balanced Accuracy and rigorous cross-validation in ensuring trustworthy results is emphasized. The survey also details diverse feature representations and the evolution of machine learning models employed. Notable real-world authorship attribution cases, such as those involving works attributed to Bach, Josquin des Prez, and Lennon–McCartney, are specifically discussed, illustrating the opportunities and pitfalls of applying computational techniques to resolve disputed musical provenance. Based on these insights, a set of actionable guidelines for future research are proposed. These recommendations are designed to significantly enhance the reliability, reproducibility, and musicological validity of composer identification and authorship attribution studies, fostering more robust and interpretable computational stylistic analysis.
- Open Access
- 18 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 302-307
Joint Learning of Emotions in Music and Generalized Sounds
In this study, we aim to determine if generalized sounds and music can share a common emotional space, improving predictions of emotion in terms of arousal and valence. We propose the use of multiple datasets as a multi-domain learning technique. Our approach involves creating a common space encompassing features that characterize both generalized sounds and music, as they can evoke emotions in a similar manner. To achieve this, we utilized two publicly available datasets, namely IADS-E and PMEmo, following a standardized experimental protocol. We employed a wide variety of features that capture diverse aspects of the audio structure including key parameters of spectrum, energy, and voicing. Subsequently, we performed joint learning on the common feature space, leveraging heterogeneous model architectures. Interestingly, this synergistic scheme outperforms the state-of-the-art in both sound and music emotion prediction. The code enabling full replication of the presented experimental pipeline is available at https://github.com/LIMUNIMI/MusicSoundEmotions.
- 18 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 302-307
Open AccessJoint Learning of Emotions in Music and Generalized Sounds
In this study, we aim to determine if generalized sounds and music can share a common emotional space, improving predictions of emotion in terms of arousal and valence. We propose the use of multiple datasets as a multi-domain learning technique. Our approach involves creating a common space encompassing features that characterize both generalized sounds and music, as they can evoke emotions in a similar manner. To achieve this, we utilized two publicly available datasets, namely IADS-E and PMEmo, following a standardized experimental protocol. We employed a wide variety of features that capture diverse aspects of the audio structure including key parameters of spectrum, energy, and voicing. Subsequently, we performed joint learning on the common feature space, leveraging heterogeneous model architectures. Interestingly, this synergistic scheme outperforms the state-of-the-art in both sound and music emotion prediction. The code enabling full replication of the presented experimental pipeline is available at https://github.com/LIMUNIMI/MusicSoundEmotions.
- Open Access
- 18 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 260-269
Optical Music Recognition in Manuscripts from the Ricordi Archive
The Ricordi archive, a prestigious collection of significant musical manuscripts from renowned opera composers such as Donizetti, Verdi and Puccini, has been digitized. This process has allowed us to automatically extract samples that represent various musical elements depicted on the manuscripts, including notes, staves, clefs, erasures, and composer’s annotations, among others. To distinguish between digitization noise and actual music elements, a subset of these images was meticulously grouped and labeled by multiple individuals into several classes. After assessing the consistency of the annotations, we trained multiple neural network-based classifiers to differentiate between the identified music elements. The primary objective of this study was to evaluate the reliability of these classifiers, with the ultimate goal of using them for the automatic categorization of the remaining unannotated data set. The dataset, complemented by manual annotations, models, and source code used in these experiments are publicly accessible for replication purposes.1
- 18 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 260-269
Open AccessOptical Music Recognition in Manuscripts from the Ricordi Archive
The Ricordi archive, a prestigious collection of significant musical manuscripts from renowned opera composers such as Donizetti, Verdi and Puccini, has been digitized. This process has allowed us to automatically extract samples that represent various musical elements depicted on the manuscripts, including notes, staves, clefs, erasures, and composer’s annotations, among others. To distinguish between digitization noise and actual music elements, a subset of these images was meticulously grouped and labeled by multiple individuals into several classes. After assessing the consistency of the annotations, we trained multiple neural network-based classifiers to differentiate between the identified music elements. The primary objective of this study was to evaluate the reliability of these classifiers, with the ultimate goal of using them for the automatic categorization of the remaining unannotated data set. The dataset, complemented by manual annotations, models, and source code used in these experiments are publicly accessible for replication purposes.1
- 7 September 2022
- Published by Springer Nature
- p. 333-345
Variational Autoencoders for Anomaly Detection in Respiratory Sounds
- 7 September 2022
- Published by Springer Nature
- p. 333-345
Variational Autoencoders for Anomaly Detection in Respiratory Sounds
- Open Access
- 13 April 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 81 (22) , 32371-32391
A perceptual measure for evaluating the resynthesis of automatic music transcriptions
This study focuses on the perception of music performances when contextual factors, such as room acoustics and instrument, change. We propose to distinguish the concept of “performance” from the one of “interpretation”, which expresses the “artistic intention”. Towards assessing this distinction, we carried out an experimental evaluation where 91 subjects were invited to listen to various audio recordings created by resynthesizing MIDI data obtained through Automatic Music Transcription (AMT) systems and a sensorized acoustic piano. During the resynthesis, we simulated different contexts and asked listeners to evaluate how much the interpretation changes when the context changes. Results show that: (1) MIDI format alone is not able to completely grasp the artistic intention of a music performance; (2) usual objective evaluation measures based on MIDI data present low correlations with the average subjective evaluation. To bridge this gap, we propose a novel measure which is meaningfully correlated with the outcome of the tests. In addition, we investigate multimodal machine learning by providing a new score-informed AMT method and propose an approximation algorithm for thep-dispersion problem.
- 13 April 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 81 (22) , 32371-32391
Open AccessA perceptual measure for evaluating the resynthesis of automatic music transcriptions
This study focuses on the perception of music performances when contextual factors, such as room acoustics and instrument, change. We propose to distinguish the concept of “performance” from the one of “interpretation”, which expresses the “artistic intention”. Towards assessing this distinction, we carried out an experimental evaluation where 91 subjects were invited to listen to various audio recordings created by resynthesizing MIDI data obtained through Automatic Music Transcription (AMT) systems and a sensorized acoustic piano. During the resynthesis, we simulated different contexts and asked listeners to evaluate how much the interpretation changes when the context changes. Results show that: (1) MIDI format alone is not able to completely grasp the artistic intention of a music performance; (2) usual objective evaluation measures based on MIDI data present low correlations with the average subjective evaluation. To bridge this gap, we propose a novel measure which is meaningfully correlated with the outcome of the tests. In addition, we investigate multimodal machine learning by providing a new score-informed AMT method and propose an approximation algorithm for thep-dispersion problem.