Back To Schedule
Wednesday, September 13 • 11:00 - 11:30
Paper: Bridging the gap between cutting edge research in audio restoration and sound archive practices

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Co-authors of this paper are Ignacio Irigaray, Federico Salles, Viviana Ruiz, and Martín Rocamora.
Since the end of the 19th century, sound recordings have increased the possibilities and scope of musicology and music documentation. In Uruguay, the figure of Lauro Ayestarán stands out, who between 1943 and 1966 made more than 3000 field recordings throughout the national territory. These recordings are kept at the Centro Nacional de Documentación Musical (CDM) and suffer from a high level of noise that can make it difficult to appreciate, thus narrowing the access. Traditional methods for digital audio restoration are based on Digital Signal Processing techniques, such as Wiener filtering and autoregressive modelling. However, the significant progress brought by deep learning to computer vision and natural language processing has also extended to the audio domain, improving the state-of-the-art in problems like speech recognition and sound source separation. Consequently, some recent works have addressed audio restoration tasks using a deep learning approach, including bandwidth extension, and denoising. This work addresses the problem of noise reduction in analog tape recordings using a deep-learning approach. First, we build a data set of audio snippets of tape noise extracted from different functional tape equipment. Then, we train a deep-learning architecture. The data set of tape noise snippets and the trained deep-learning models are publicly available. In this way, we encourage the collective improvement of the data set and the broad application of the denoising approach by the audiovisual archives community. This interdisciplinary work is carried out by archive researchers from the CDM and signal processing researchers from the Universidad de la República (Uruguay).

avatar for Ignacio Irigaray

Ignacio Irigaray

Universidad de la República / Centro Nacional de Documentación Musical
Hi, I am a musician, professor and electrical engineer using machine learning for audio signal restoration.  I am glad to be at the IASA conference and to be able to share experiences with the other participants.

avatar for Pedro Félix

Pedro Félix

Coordinator, National Sound Archive - Installation team
Pedro Félix is the coordinator of the Installing Team of the National Sound Archive, a structure created by the Portuguese Government (http://arquivonacionaldosom.gov.pt).He is a member of research centres at Universidade Nova de Lisboa (since 1997) and collaborated with the Fado Museum (since 2005).He was part of the team responsible for the preparation of the Fado proposal to UNESCO Intangible Cultural Heritage (2005-2011, coordinating fieldwork... Read More →

Wednesday September 13, 2023 11:00 - 11:30 GMT+03
Doctorate Hall 2 (D2)