Niccolò Pretto
Free University of Bozen-Bolzano, Computer Science, Department Member
- Consiglio Nazionale delle Ricerche (CNR), Institute for Computational Linguistics, Department Memberadd
- Niccolò Pretto completed his PhD at the Department of Information Engineering, University of Padova. His research is ... moreNiccolò Pretto completed his PhD at the Department of Information Engineering, University of Padova. His research is primarily focused on sound and music computing, and preservation and access to historical audio documents and cultural heritage in general. More specifically, his work consists of research and development of innovative methodologies, and applications to preserve, analyze, and experience musical heritage. His work is highly multidisciplinary; during his research he has collaborated with engineers, as well as musicologists, archaeologists, archivists, psychologists, architects, earth scientists, and physicians. Additionally, his research has included the adoption of several technologies and methods extending to web and mobile interfaces, embedded systems, and machine learning techniques.edit
This paper presents a workflow and novel digital filters for compensating speed and equalization errors that can impact digitized audio open-reel tapes. We examine three frequent cases of mismatch between recording and reproducing... more
This paper presents a workflow and novel digital filters for compensating speed and equalization errors that can impact digitized audio open-reel tapes. We examine three frequent cases of mismatch between recording and reproducing standards: NAB 3.75 ips-CCIR 7.5 ips; NAB 3.75 ips-CCIR 15 ips; NAB 7.5 ips-CCIR 15 ips. Three MUSHRA-inspired tests (” sets”) containing≥ 21 participants were used to perceptually assess the workflow and digital filters, using excerpts of music and voice. The results indicated that the digital correction filters performed well, although the electroacoustic stimuli in Set C provided mixed results, suggesting that the style of the music used in perception tests should not be overlooked.
Research Interests:
While there are currently various approaches that define and adapt the conditions in which the user experiences content or service for several music and audio-related applications including entertainment, communication, audio documents... more
While there are currently various approaches that define and adapt the conditions in which the user experiences content or service for several music and audio-related applications including entertainment, communication, audio documents preservation/restoration, we are missing worldwide accepted standards that enable data exchange and interoperability based on common interfaces for such applications. The Moving Picture, Audio and Data Coding by Artificial Intelligence (MPAI) is an international non-profit organization whose mission is to develop such standards. Relying on Artificial Intelligence (AI), MPAI creates a workflow of AI Modules (AIM) that are interchangeable and upgradable without necessarily changing the logic of the application. A specific area of work, MPAI Context-based Audio Enhancement (MPAI-CAE), is showing tremendous possibilities for the Sound and Music Computing (SMC) community. MPAI-CAE applies context information to the input content to deliver the audio output via the most appropriate protocol. Three MPAI-CAE case studies particularly relevant for the SMC community will be presented in this paper: Audio recording preservation (ARP), a use case that covers the whole "philologically informed" archival process of an audio document, from the active sound documents preservation to the access to digitized files; Audio-on-the-go (AOG), which aims to improve safety and listening quality for situations in which the users are in motion in different environments; and Emotion-enhanced speech (EES), a use case that implements a user-friendly system control interface that generates speech with various levels of emotions.
Research Interests:
The lack of a standard preservation methodology is an important issue that digital speech archives have to face nowadays. Information that needs to be stored requires the implementation of a methodological framework in order to prevent... more
The lack of a standard preservation methodology is an important issue that digital speech archives have to face nowadays. Information that needs to be stored requires the implementation of a methodological framework in order to prevent cultural losses. The Centro di Sonologia Computazionale (CSC) of the University of Padova, cooperating with several digital archives (both speech and music) implemented a scientific methodology for the active preservation of audio documents. The framework is still a work in progress and the methodology is continuously improved with new additions, such as neural networks and machine learning-based techniques for detecting the right equalization curves or recognizing discontinuities on the tape. This contribution presents the abovementioned methodology,
as well as several informatics tools for the study, the access and the preservation of audio documents.
as well as several informatics tools for the study, the access and the preservation of audio documents.
Research Interests:
In the medieval Islamic territories of the Iberian Peninsula known as Al-Andalus a unique style of music was formed combining local practices with Arab sensibilities. After the fall of the last An-dalusian kingdom, this classical... more
In the medieval Islamic territories of the Iberian Peninsula known as Al-Andalus a unique style of music was formed combining local practices with Arab sensibilities. After the fall of the last An-dalusian kingdom, this classical repertoire has been preserved to the present in North African countries. The idiosyncrasies of this repertoire, which combines musical traits from Western and Eastern Mediterranean traditions in orchestral and choral settings, as well as instrumental and vocal solos, deserves an in depth musico-logical study, that can benefit from computational tools for corpus-driven research. On the other hand, the characteristics of this music poses interesting challenges to MIR methods and therefore offer new research opportunities to this field. To address these topics, we present here the first complete release of the corpus for the research of the Moroccan tradition of Arab-Andalusian music built in the framework of the CompMusic project. The corpus comprises three data collections, namely audio recordings, music scores and lyrics, as well as related annotations and metadata. We also present a series of Jupyter Notebooks for browsing and retrieving data from the corpus. Both the corpus and notebooks are completely open to the research community.
Research Interests:
Questo articolo descrive un progetto relativo all’implementazione di un flauto di Pan virtuale all’interno di una installazione museale che verrà esposta presso il Museo di Scienze Archeologiche e d’Arte dell’Università degli Studi di... more
Questo articolo descrive un progetto relativo all’implementazione di un flauto di Pan virtuale all’interno di una installazione museale che verrà esposta presso il Museo di Scienze Archeologiche e d’Arte dell’Università degli Studi di Padova. In primo luogo, l’articolo introduce il problema della conservazione attiva e della valorizzazione degli strumenti in ambito museale. A seguire descrive l’installazione multimediale progettata appositamente per valorizzare un antico flauto di Pan ritrovato in Egitto, negli anni Trenta, durante una campagna di scavi archeologici. Il reperto è stato sottoposto a svariate analisi, quali scansioni 3D e Tomografia Computerizzata, da cui sono state estratte le
misure interne ed esterne del flauto. Queste sono state indispensabili
per ricavare l’intonazione delle canne e quindi creare il modello alla base del flauto virtuale. Infine, l’articolo descrive in maniera approfondita le scelte progettuali, le modalità di interazione e l’implementazione delle due sezioni dell’installazione dedicata al suono. L’utente, infatti, può “suonare” il flauto utilizzando come input sia i comandi touch, sia il “soffio”.
misure interne ed esterne del flauto. Queste sono state indispensabili
per ricavare l’intonazione delle canne e quindi creare il modello alla base del flauto virtuale. Infine, l’articolo descrive in maniera approfondita le scelte progettuali, le modalità di interazione e l’implementazione delle due sezioni dell’installazione dedicata al suono. L’utente, infatti, può “suonare” il flauto utilizzando come input sia i comandi touch, sia il “soffio”.
Research Interests:
This paper presents ongoing work aimed at realizing an interactive museum installation that aids museum visitors learn about a musical instrument that is part of the exhibit: an exceptionally well preserved ancient Pan... more
This paper presents ongoing work aimed at realizing an interactive museum installation that aids museum visitors learn about a musical instrument that is part of the exhibit: an exceptionally well preserved ancient Pan flute, most probably of Greek origins. The paper first discusses the approach to non-invasive analysis on the instrument, which was based on 3D scanning using computerized tomography (CT scan), and provided the starting point to inspect the geometry and some aspects of the construction of the instrument. A tentative reconstruction of the instrument tuning is then presented, which is based on the previous analysis and on elements of theory of ancient Greek music. Finally, the paper presents the design approach and the first results regarding the interactive museum installation that recreates the virtual flute and allows intuitive access to several related research facets.
Research Interests:
Questo articolo presenta una virtualizzazione di un grammofono per la riproduzione di dischi fonografici digitalizzati, realizzata utilizzando tecnologia web. Il lavoro introduce il problema della conservazione attiva dei dispositivi per... more
Questo articolo presenta una virtualizzazione di un grammofono per la riproduzione di dischi fonografici digitalizzati, realizzata utilizzando tecnologia web. Il lavoro introduce il problema della conservazione attiva dei dispositivi per la riproduzione di documenti sonori, risaltando la centralità dell'aspetto filologico nella fruizione. La web-application riproduce fedelmente il funzionamento del grammofono, attraverso una interfaccia utente intuitiva che ne rappresenta graficamente tutte le componenti meccaniche. La descrizione delle tecnologie alla base dell'applicazione si sofferma sulle librerie Web Audio Api, fondamentali per ricostruire le peculiarità sonore che contraddistinguono i grammofoni per dischi in gommalacca. Nei primi anni del Novecento la mancanza di uno standard univoco per l'incisione di registrazioni fonografiche ha favorito la proliferazione di un enorme varietà di curve di equalizzazione e velocità di rotazione dei dischi: la virtualizzazione propone una soluzione flessibile per adattare in tempo reale i brani digitalizzati alle caratteristiche del supporto originale.
Research Interests:
This article presents a methodology for the active preservation of, and the access to, magnetic tapes of audio archives. The methodology has been defined and implemented by a multidisciplinary team involving engineers as well as... more
This article presents a methodology for the active preservation of, and the access to, magnetic tapes of audio archives. The methodology has been defined and implemented by a multidisciplinary team involving engineers as well as musicians, composers and archivists. The strong point of the methodology is the philological awareness that influenced the development of digital tools, which consider the critical questions in the historian and musicologist's approach: the secondary information and the history of transmission of an audio document.
The aim of this article is to present and discuss an innovative methodology aimed at accessing digitized copies of historical tape music audio documents; the methodology leverages on the multimedia and multisensory capabilities of mobile... more
The aim of this article is to present and discuss an innovative methodology aimed at accessing digitized copies of historical tape music audio documents; the methodology leverages on the multimedia and multisensory capabilities of mobile devices to provide an unprecedented level of fruition. In addition to the methodology, and stemming from it, we present an actual software application for Android tablet devices. This novel piece of software was designed and developed in a multidisciplinary team involving engineers as well asmusicians, composers, and archivists. The strongest element in our work is the fact that it follows a rigorous process and it is based on the principles of philological awareness; thus, it also takes into consideration the critical points in the musicologist's domain such as (i) the definition of preservation (i.e., master) copy, (ii) the importance of secondary information, (iii) the history of production and transmission of audio documents.
Information engineering has always expanded its scope by inspiring innovation in different scientific disciplines. In particular, in the last sixty years, music and engineering have forged a is a paradigmatic case that includes several... more
Information engineering has always expanded its scope by inspiring innovation in different scientific disciplines. In particular, in the last sixty years, music and engineering have forged a is a paradigmatic case that includes several multi-faceted cultural artifacts and traditions. Several issues arise from the analog-digital transfer of cultural objects, concerning their creation, preservation, strong connection in the discipline known as “Sound and Music Computing”. Musical heritage access, analysis and experiencing. The keystone is the relationship of these digitized cultural objects with their carrier and cultural context. The terms “cultural context” and “cultural context awareness” are delineated, alongside the concepts of contextual information and metadata. Since they maintain the integrity of the object, its meaning and cultural context, their role is critical. This thesis explores three main case studies concerning historical audio recordings and ancient musical instruments, aiming to delineate models to preserve, analyze, access and experience the digital versions of these three prominent examples of musical heritage. The first case study concerns analog magnetic tapes, and, in particular, tape music, a particular experimental music born in the second half of the XX century. This case study has relevant implications from the musicology, philology and archivists’ points of view, since the carrier has a paramount role and the tight connection with its content can easily break during the digitization process or the access phase. With the aim to help musicologists and audio technicians in their work, several tools based on Artificial Intelligence are evaluated in tasks such as the discontinuity detection and equalization recognition. By considering the peculiarities of tape music, the philological problem of stemmatics in digitized audio documents is tackled: an algorithm based on phylogenetic techniques is proposed and assessed, confirming the suitability of these techniques for this task. Then, a methodology for a historically faithful access to digitized tape music recordings is introduced, by considering contextual information and its relationship with the carrier and the replay device. Based on this methodology, an Android app which virtualizes a tape recorder is presented, together with its assessment. Furthermore, two web applications are proposed to faithfully experience digitized 78 rpm discs and magnetic tape recordings, respectively. Finally, a prototype of web application for musicological analysis is presented. This aims to concentrate relevant part of the knowledge acquired in this work into a single interface. The second case study is a corpus of Arab-Andalusian music, suitable for computational research, which opens new opportunities to musicological studies by applying data-driven analysis. The description of the corpus is based on the five criteria formalized in the CompMusic project of the University Pompeu Fabra of Barcelona: purpose, coverage, completeness, quality and re-usability. Four Jupyter notebooks were developed with the aim to provide a useful tool for computational musicologists for analyzing and using data and metadata of such corpus. The third case study concerns an exceptional historical musical instrument: an ancient Pan flute exhibited at the Museum of Archaeological Sciences and Art of the University of Padova. The final objective was the creation of a multimedia installation to valorize this precious artifact and to allow visitors to interact with the archaeological find and to learn its history. The case study provided the opportunity to study a methodology suitable for the valorization of this ancient musical instrument, but also extendible to other artifacts or museum collections. Both the methodology and the resulting multimedia installation are presented, followed by the assessment carried out by a multidisciplinary group of experts.