Goffredo Haus

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.

Multi-layer formats are becoming increasingly important in the field of music description. Thanks to their adoption, it is possible to embed into a unique digital document different representations of music contents, multiple in number and potentially heterogeneous in media type. Moreover, these descriptions can be mutually synchronized, thus providing different views of the same information entity with a customizable level of granularity. Standard use cases of multi-layer formats for music address information structuring and support to advanced fruition. The goal of the paper is to demonstrate how suitable multi-layer formats can foster analytical activities in the field of interpretative modelling and expressiveness investigation, discussing both the pedagogical roots and the educational implications of this approach. A use case focusing on the incipit of G. Mahler’s Symphony No. 5 will be presented.

Web technologies are quickly evolving in order to provide an increasing set of services to Internet users. Multimedia is one of the fields where the availability of high-speed networks, innovative devices and new technological approaches is noticeably arousing the interest of content producers and consumers. In this regard, it is worth mentioning new HTML5 elements to embed multimedia, recent evolutions of e-book formats towards interactivity and hypermedia, and the establishment of new W3C groups addressing specific media-related issues. Such technological advances can have a deep impact on digital cultures, as it regards both content production and dissemination on the Web. The current challenge is to combine new hardware and software technologies in order to radically improve and customize content experience. After discussing a number of approaches to music representation, this paper aims to review the most relevant Web technologies already available and to propose new Web applications addressing music in an advanced multimedia context.

This paper tries to outline the evolution of the role of ICT with respect to Cultural Heritage showing how, starting from the first digitization projects, ICT has gradually become the major driving force for both preserving and exploiting Cultural Heritage. Specifically, the key role of advances in automatic recognition within texts and multimedia information are considered. Essential Website References Cultural Heritage Search EngineDublin Core Metadata Initiative (DCMI)Federal Agencies Digitization Guidelines Initiative (FADGI)IEEE1599International Federation of Library Associations and Institutions (IFLA)Journal on Computing and Cultural Heritage (JOCCH), ACM, New YorkJournal of Cultural Heritage, Elsevier, Amsterdam, NLLibrary of Congress, Washington, USAMPEG official siteUNESCO - Intangible Cultural HeritageUNIMARCWorld Wide Web Consortium (W3C) - Web Accessibility Initiative (WAI) Videos Click on the thumbnails below to open videos on YouTube.An Advanced Technology for Music ContentsDigital Archives for Music Cultural HeritageDigitizing Audio, Scores, and Iconographic Materials

The focus of this paper is on the integration of audio resources with other content types in digital libraries. As a case study, we will present the most recent initiative of the Biblioteca Europea di Informazione e Cultura (BEIC), an Italian institution that pursues educational and instructional goals through the realization and management of a multimedia, free access, open shelf library. A new audio section will be added to the already-existing digital archive, allowing users to listen to about 1000 classical recordings in a multi-platform and cross-browser manner. This experience involves a number of heterogeneous fields, ranging from musicology to computer programming, from cataloging to digitization and archiving. In this paper, we will apply a bottom-up technique in order to provide a generalization of the specific case study, thus suggesting a methodological approach for similar initiatives.