Stavros Ntalampiras

Federico Simonetta, Francesca Certo, Stavros Ntalampiras

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.

Michele Cozzatti, Federico Simonetta, Stavros Ntalampiras

This paper proposes a weakly-supervised machine learning-based approach aiming at a tool to alert patients about possible respiratory diseases. Various types of pathologies may affect the respiratory system, potentially leading to severe diseases and, in certain cases, death. In general, effective prevention practices are considered as major actors towards the improvement of the patient's health condition. The proposed method strives to realize an easily accessible tool for the automatic diagnosis of respiratory diseases. Specifically, the method leverages Variational Autoencoder architectures permitting the usage of training pipelines of limited complexity and relatively small-sized datasets. Importantly, it offers an accuracy of 57 %, which is in line with the existing strongly-supervised approaches.

Alessandro Maria Poirè, Federico Simonetta, Stavros Ntalampiras

The purpose of this paper is to compare different learnable frontends in medical acoustics tasks. A framework has been implemented to classify human respiratory sounds and heartbeats in two categories, i.e. healthy or affected by pathologies. After obtaining two suitable datasets, we proceeded to classify the sounds using two learnable state-of-art frontends -- LEAF and nnAudio -- plus a non-learnable baseline frontend, i.e. Mel-filterbanks. The computed features are then fed into two different CNN models, namely VGG16 and EfficientNet. The frontends are carefully benchmarked in terms of the number of parameters, computational resources, and effectiveness. This work demonstrates how the integration of learnable frontends in neural audio classification systems may improve performance, especially in the field of medical acoustics. However, the usage of such frameworks makes the needed amount of data even larger. Consequently, they are useful if the amount of data available for training is adequately large to assist the feature learning process.

Federico Simonetta, Rishav Mondal, Luca Andrea Ludovico et al.

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.

Federico Simonetta, Stavros Ntalampiras, Federico Avanzini

This paper describes an open-source Python framework for handling datasets for music processing tasks, built with the aim of improving the reproducibility of research projects in music computing and assessing the generalization abilities of machine learning models. The framework enables the automatic download and installation of several commonly used datasets for multimodal music processing. Specifically, we provide a Python API to access the datasets through Boolean set operations based on particular attributes, such as intersections and unions of composers, instruments, and so on. The framework is designed to ease the inclusion of new datasets and the respective ground-truth annotations so that one can build, convert, and extend one's own collection as well as distribute it by means of a compliant format to take advantage of the API. All code and ground-truth are released under suitable open licenses.

Nicolas Facchinetti, Federico Simonetta, Stavros Ntalampiras

Speech emotion recognition (SER) is constantly gaining attention in recent years due to its potential applications in diverse fields and thanks to the possibility offered by deep learning technologies. However, recent studies have shown that deep learning models can be vulnerable to adversarial attacks. In this paper, we systematically assess this problem by examining the impact of various adversarial white-box and black-box attacks on different languages and genders within the context of SER. We first propose a suitable methodology for audio data processing, feature extraction, and CNN-LSTM architecture. The observed outcomes highlighted the significant vulnerability of CNN-LSTM models to adversarial examples (AEs). In fact, all the considered adversarial attacks are able to significantly reduce the performance of the constructed models. Furthermore, when assessing the efficacy of the attacks, minor differences were noted between the languages analyzed as well as between male and female speech. In summary, this work contributes to the understanding of the robustness of CNN-LSTM models, particularly in SER scenarios, and the impact of AEs. Interestingly, our findings serve as a baseline for a) developing more robust algorithms for SER, b) designing more effective attacks, c) investigating possible defenses, d) improved understanding of the vocal differences between different languages and genders, and e) overall, enhancing our comprehension of the SER task.

Federico Simonetta, Stavros Ntalampiras, Federico Avanzini

Motivated by the state-of-art psychological research, we note that a piano performance transcribed with existing Automatic Music Transcription (AMT) methods cannot be successfully resynthesized without affecting the artistic content of the performance. This is due to 1) the different mappings between MIDI parameters used by different instruments, and 2) the fact that musicians adapt their way of playing to the surrounding acoustic environment. To face this issue, we propose a methodology to build acoustics-specific AMT systems that are able to model the adaptations that musicians apply to convey their interpretation. Specifically, we train models tailored for virtual instruments in a modular architecture that takes as input an audio recording and the relative aligned music score, and outputs the acoustics-specific velocities of each note. We test different model shapes and show that the proposed methodology generally outperforms the usual AMT pipeline which does not consider specificities of the instrument and of the acoustic environment. Interestingly, such a methodology is extensible in a straightforward way since only slight efforts are required to train models for the inference of other piano parameters, such as pedaling.

Federico Simonetta, Federico Avanzini, Stavros Ntalampiras

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 the $p$-dispersion problem.

Marco Colussi, Stavros Ntalampiras

After constructing a deep neural network for urban sound classification, this work focuses on the sensitive application of assisting drivers suffering from hearing loss. As such, clear etiology justifying and interpreting model predictions comprise a strong requirement. To this end, we used two different representations of audio signals, i.e. Mel and constant-Q spectrograms, while the decisions made by the deep neural network are explained via layer-wise relevance propagation. At the same time, frequency content assigned with high relevance in both feature sets, indicates extremely discriminative information characterizing the present classification task. Overall, we present an explainable AI framework for understanding deep urban sound classification.

Federico Simonetta, Stavros Ntalampiras, Federico Avanzini

Audio-to-score alignment (A2SA) is a multimodal task consisting in the alignment of audio signals to music scores. Recent literature confirms the benefits of Automatic Music Transcription (AMT) for A2SA at the frame-level. In this work, we aim to elaborate on the exploitation of AMT Deep Learning (DL) models for achieving alignment at the note-level. We propose a method which benefits from HMM-based score-to-score alignment and AMT, showing a remarkable advancement beyond the state-of-the-art. We design a systematic procedure to take advantage of large datasets which do not offer an aligned score. Finally, we perform a thorough comparison and extensive tests on multiple datasets.

Michelangelo Acconcjaioco, Stavros Ntalampiras

This work introduces the one-shot learning paradigm in the computational bioacoustics domain. Even though, most of the related literature assumes availability of data characterizing the entire class dictionary of the problem at hand, that is rarely true as a habitat's species composition is only known up to a certain extent. Thus, the problem needs to be addressed by methodologies able to cope with non-stationarity. To this end, we propose a framework able to detect changes in the class dictionary and incorporate new classes on the fly. We design an one-shot learning architecture composed of a Siamese Neural Network operating in the logMel spectrogram space. We extensively examine the proposed approach on two datasets of various bird species using suitable figures of merit. Interestingly, such a learning scheme exhibits state of the art performance, while taking into account extreme non-stationarity cases.

Axel Chemla--Romeu-Santos, Stavros Ntalampiras, Philippe Esling et al.

Extraction of symbolic information from signals is an active field of research enabling numerous applications especially in the Musical Information Retrieval domain. This complex task, that is also related to other topics such as pitch extraction or instrument recognition, is a demanding subject that gave birth to numerous approaches, mostly based on advanced signal processing-based algorithms. However, these techniques are often non-generic, allowing the extraction of definite physical properties of the signal (pitch, octave), but not allowing arbitrary vocabularies or more general annotations. On top of that, these techniques are one-sided, meaning that they can extract symbolic data from an audio signal, but cannot perform the reverse process and make symbol-to-signal generation. In this paper, we propose an bijective approach for signal/symbol translation by turning this problem into a density estimation task over signal and symbolic domains, considered both as related random variables. We estimate this joint distribution with two different variational auto-encoders, one for each domain, whose inner representations are forced to match with an additive constraint, allowing both models to learn and generate separately while allowing signal-to-symbol and symbol-to-signal inference. In this article, we test our models on pitch, octave and dynamics symbols, which comprise a fundamental step towards music transcription and label-constrained audio generation. In addition to its versatility, this system is rather light during training and generation while allowing several interesting creative uses that we outline at the end of the article.

Federico Simonetta, Carlos Cancino-Chacón, Stavros Ntalampiras et al.

In many musical traditions, the melody line is of primary significance in a piece. Human listeners can readily distinguish melodies from accompaniment; however, making this distinction given only the written score -- i.e. without listening to the music performed -- can be a difficult task. Solving this task is of great importance for both Music Information Retrieval and musicological applications. In this paper, we propose an automated approach to identifying the most salient melody line in a symbolic score. The backbone of the method consists of a convolutional neural network (CNN) estimating the probability that each note in the score (more precisely: each pixel in a piano roll encoding of the score) belongs to the melody line. We train and evaluate the method on various datasets, using manual annotations where available and solo instrument parts where not. We also propose a method to inspect the CNN and to analyze the influence exerted by notes on the prediction of other notes; this method can be applied whenever the output of a neural network has the same size as the input.

Federico Simonetta, Stavros Ntalampiras, Federico Avanzini

Towards improving the performance in various music information processing tasks, recent studies exploit different modalities able to capture diverse aspects of music. Such modalities include audio recordings, symbolic music scores, mid-level representations, motion, and gestural data, video recordings, editorial or cultural tags, lyrics and album cover arts. This paper critically reviews the various approaches adopted in Music Information Processing and Retrieval and highlights how multimodal algorithms can help Music Computing applications. First, we categorize the related literature based on the application they address. Subsequently, we analyze existing information fusion approaches, and we conclude with the set of challenges that Music Information Retrieval and Sound and Music Computing research communities should focus in the next years.