Stefano Fasciani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Stefano Fasciani has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Christian Ritz
School of Electrical, Computer and Telecommunications Engineering, University of Wollongong, Wollongong 2522, Australia
2 shared publications - Kyrre Glette
University of Oslo, Oslo, Norway
2 shared publications - Nidhal Abdulaziz
Faculty of Engineering and Information Sciences, University of Wollongong in Dubai, Dubai 20183, United Arab Emirates
2 shared publications - Abigail Copiaco
College of Engineering and Information Technology, University of Dubai, Dubai 14143, United Arab Emirates
1 shared publication - Abigail Copiaco1 shared publication
- Alex Szorkovszky
Simula Research Laboratory, Oslo, Norway
1 shared publication
Latest Publications
- Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 255-269
An Interactive Self-Assembly Swarm Music System in Extended Reality
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 255-269
Open AccessAn Interactive Self-Assembly Swarm Music System in Extended Reality
- 29 March 2024
- Published by Springer Nature
- p. 211-227
Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs
- 29 March 2024
- Published by Springer Nature
- p. 211-227
Towards Sound Innovation Engines Using Pattern-Producing Networks and Audio Graphs
- Open Access
- 16 June 2022
- Published by PubPub
A Toolkit for the Analysis of the NIME Proceedings Archive
This paper describes a toolkit for analyzing the NIME proceedings archive, which facilitates the bibliometric study of the conference papers and the identification of trends and patterns. The toolkit is implemented as a collection of Python methods that aggregate, scrape and retrieve various meta-data from published papers. Extracted data is stored in a large numeric table as well as plain text files. Analytical functions within the toolkit can be easily extended or modified. The text mining script that can be highly customized without the need for programming. The toolkit uses only publicly available information organized in standard formats, and is available as open-source software to promote continuous development in step with the NIME archive.
- 16 June 2022
- Published by PubPub
Open AccessA Toolkit for the Analysis of the NIME Proceedings Archive
This paper describes a toolkit for analyzing the NIME proceedings archive, which facilitates the bibliometric study of the conference papers and the identification of trends and patterns. The toolkit is implemented as a collection of Python methods that aggregate, scrape and retrieve various meta-data from published papers. Extracted data is stored in a large numeric table as well as plain text files. Analytical functions within the toolkit can be easily extended or modified. The text mining script that can be highly customized without the need for programming. The toolkit uses only publicly available information organized in standard formats, and is available as open-source software to promote continuous development in step with the NIME archive.
- Open Access
- 19 July 2021
- Published by PubPub
20 NIMEs: Twenty Years of New Interfaces for Musical Expression
This paper provides figures and metrics over twenty years of New Interfaces for Musical Expression conferences, which are derived by analyzing the publicly available paper proceedings. Besides presenting statistical information and a bibliometric study, we aim at identifying trends and patterns. The analysis shows the growth and heterogeneity of the NIME demographic, as well the increase in research output. The data presented in this paper allows the community to reflect on several issues such as diversity and sustainability, and it provides insights to address challenges and set future directions.
- 19 July 2021
- Published by PubPub
Open Access20 NIMEs: Twenty Years of New Interfaces for Musical Expression
This paper provides figures and metrics over twenty years of New Interfaces for Musical Expression conferences, which are derived by analyzing the publicly available paper proceedings. Besides presenting statistical information and a bibliometric study, we aim at identifying trends and patterns. The analysis shows the growth and heterogeneity of the NIME demographic, as well the increase in research output. The data presented in this paper allows the community to reflect on several issues such as diversity and sustainability, and it provides insights to address challenges and set future directions.
- Open Access
- 26 May 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (11) , 4880
A Study of Features and Deep Neural Network Architectures and Hyper-Parameters for Domestic Audio Classification
Recent methodologies for audio classification frequently involve cepstral and spectral features, applied to single channel recordings of acoustic scenes and events. Further, the concept of transfer learning has been widely used over the years, and has proven to provide an efficient alternative to training neural networks from scratch. The lower time and resource requirements when using pre-trained models allows for more versatility in developing system classification approaches. However, information on classification performance when using different features for multi-channel recordings is often limited. Furthermore, pre-trained networks are initially trained on bigger databases and are often unnecessarily large. This poses a challenge when developing systems for devices with limited computational resources, such as mobile or embedded devices. This paper presents a detailed study of the most apparent and widely-used cepstral and spectral features for multi-channel audio applications. Accordingly, we propose the use of spectro-temporal features. Additionally, the paper details the development of a compact version of the AlexNet model for computationally-limited platforms through studies of performances against various architectural and parameter modifications of the original network. The aim is to minimize the network size while maintaining the series network architecture and preserving the classification accuracy. Considering that other state-of-the-art compact networks present complex directed acyclic graphs, a series architecture proposes an advantage in customizability. Experimentation was carried out through Matlab, using a database that we have generated for this task, which composes of four-channel synthetic recordings of both sound events and scenes. The top performing methodology resulted in a weighted F1-score of 87.92% for scalogram features classified via the modified AlexNet-33 network, which has a size of 14.33 MB. The AlexNet network returned 86.24% at a size of 222.71 MB.
- 26 May 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (11) , 4880
Open AccessA Study of Features and Deep Neural Network Architectures and Hyper-Parameters for Domestic Audio Classification
Recent methodologies for audio classification frequently involve cepstral and spectral features, applied to single channel recordings of acoustic scenes and events. Further, the concept of transfer learning has been widely used over the years, and has proven to provide an efficient alternative to training neural networks from scratch. The lower time and resource requirements when using pre-trained models allows for more versatility in developing system classification approaches. However, information on classification performance when using different features for multi-channel recordings is often limited. Furthermore, pre-trained networks are initially trained on bigger databases and are often unnecessarily large. This poses a challenge when developing systems for devices with limited computational resources, such as mobile or embedded devices. This paper presents a detailed study of the most apparent and widely-used cepstral and spectral features for multi-channel audio applications. Accordingly, we propose the use of spectro-temporal features. Additionally, the paper details the development of a compact version of the AlexNet model for computationally-limited platforms through studies of performances against various architectural and parameter modifications of the original network. The aim is to minimize the network size while maintaining the series network architecture and preserving the classification accuracy. Considering that other state-of-the-art compact networks present complex directed acyclic graphs, a series architecture proposes an advantage in customizability. Experimentation was carried out through Matlab, using a database that we have generated for this task, which composes of four-channel synthetic recordings of both sound events and scenes. The top performing methodology resulted in a weighted F1-score of 87.92% for scalogram features classified via the modified AlexNet-33 network, which has a size of 14.33 MB. The AlexNet network returned 86.24% at a size of 222.71 MB.
- Open Access
DASEE A Synthetic Database of Domestic Acoustic Scenes and Events in Dementia Patients Environment
Access to informative databases is a crucial part of notable research developments. In the field of domestic audio classification, there have been significant advances in recent years. Although several audio databases exist, these can be limited in terms of the amount of information they provide, such as the exact location of the sound sources, and the associated noise levels. In this work, we detail our approach on generating an unbiased synthetic domestic audio database, consisting of sound scenes and events, emulated in both quiet and noisy environments. Data is carefully curated such that it reflects issues commonly faced in a dementia patients environment, and recreate scenarios that could occur in real-world settings. Similarly, the room impulse response generated is based on a typical one-bedroom apartment at Hebrew SeniorLife Facility. As a result, we present an 11-class database containing excerpts of clean and noisy signals at 5-seconds duration each, uniformly sampled at 16 kHz. Using our baseline model using Continues Wavelet Transform Scalograms and AlexNet, this yielded a weighted F1-score of 86.24 percent.
Open AccessDASEE A Synthetic Database of Domestic Acoustic Scenes and Events in Dementia Patients Environment
Access to informative databases is a crucial part of notable research developments. In the field of domestic audio classification, there have been significant advances in recent years. Although several audio databases exist, these can be limited in terms of the amount of information they provide, such as the exact location of the sound sources, and the associated noise levels. In this work, we detail our approach on generating an unbiased synthetic domestic audio database, consisting of sound scenes and events, emulated in both quiet and noisy environments. Data is carefully curated such that it reflects issues commonly faced in a dementia patients environment, and recreate scenarios that could occur in real-world settings. Similarly, the room impulse response generated is based on a typical one-bedroom apartment at Hebrew SeniorLife Facility. As a result, we present an 11-class database containing excerpts of clean and noisy signals at 5-seconds duration each, uniformly sampled at 16 kHz. Using our baseline model using Continues Wavelet Transform Scalograms and AlexNet, this yielded a weighted F1-score of 86.24 percent.
- 30 April 2020
- Published by Romania ADL Association
- Vol. 1, 612-620
STUDENT ACTIVE LEARNING IN A TWO CAMPUS ORGANISATION
- 30 April 2020
- Published by Romania ADL Association
- Vol. 1, 612-620
STUDENT ACTIVE LEARNING IN A TWO CAMPUS ORGANISATION